Class of 2019

STUDENT RESUME BOOK

[email protected] CLASS OF 2019 PROFILE 46 48% WOMEN CLASS SIZE

PRIOR COMPANIES Feldsted & Scolney 2 Amazon.com, Inc Fincare Small Finance Bank American Airlines Group General Electric Co AVERAGE YEARS American Family Insurance Mu Sigma, Inc PRIOR WORK Bank of New York, Qualtrics LLC EXPERIENCE Melloncorp Quantiphi Inc Brookhurst Insurance Skyline Technologies Services TechLoss Consulting & CEB Inc Restoration, Inc Cecil College ThoughtWorks, Inc Darwin Labs US Army Economists, Inc UCSD Guardian United Health Group, Inc PRIOR DEGREE Welch Consulting, Ltd CONCENTRATIONS ZS Associates Inc & BACKGROUND*

MATH & STATISTICS 82.61% ENGINEERING 32.61% ECONOMICS 30.43% COMPUTER SCIENCE & IT 19.57% SOCIAL SCIENCES 13.04% HUMANITIES 10.87% BUSINESS 8.70% OTHER SCIENCES 8.70% *many students had multiple majors or OTHER 8.70% specializations; for example, of the 82.61% of students with a math and/or statistics DATA SCIENCE 2.17% background, most had an additional major or concentration and therefore are represented in additional categories.

0 20 40 60 80 100 Class of 2019

SAURABH ANNADATE ALICIA BURRIS ALEX BURZINSKI TED CARLSON

IVAN CHEN ANGELA CHEN CARSON CHEN HARISH CHOCKALINGAM

SABARISH CHOCKALINGAM TONY COLUCCI JD COOK SOPHIE DU

JAMES FAN MICHAEL FEDELL JOYCE FENG NATHAN FRANKLIN

TIAN FU ELLIOT GARDNER MAX HOLIBER NAOMI KADUWELA

MATT KEHOE JOE KUPRESANIN MICHEL LEROY JONATHAN LEWYCKYJ Class of 2019

HENRY PARK KAREN QIAN FINN QIAO RACHEL ROSENBERG

SHREYAS SABNIS SURABHI SETH TOVA SIMONSON MOLLY SROUR

DHANSREE SURAJ TANYA TANDON KATIE TANG MARCUS THUILLIER

SHIVA RAM VENKAT RAMANAN ARPAN VENUGOPAL ANJALI VERMA ZIYING WANG

CLAUDIA XU NORA XU YIWEI ZHANG SHARON ZHANG

EILEEN ZHANG YUCHENG ZHU SAURABH ANNADATE (773) 564-3568 | [email protected] | github.com/saurabhannadate93

Education Master of Science in Analytics, Northwestern University; GPA: 4.0/4.0 Sep 2018 – Dec 2019 • Coursework: Databases and Information Retrieval, Predictive Analytics (Supervised Learning), Data Mining (Unsupervised Learning, Recommender Systems), Big Data (Hadoop, MapReduce, Spark), Deep Learning, Data Visualization (D3 and Tableau), Text Analytics, Analytics Value Chain (Deployment, Cloud Computing)

B.E. (Hons.) Mechanical Engineering, Birla Institute of Technology & Science, Pilani; GPA: 8.9/10.0 Aug 2011 – Jul 2015

Qualifications & Skills • Passed Level 1 CFA (Chartered Financial Analyst) exam in December 2016 • Languages and Tools: Python, R, SQL, Java, VBA, SAS, Hadoop, MapReduce, Spark, Git, AWS, D3.js, Tableau, Excel

Professional Experience Data Science Intern, Capital One Jun 2019 – Aug 2019 • Built pipelines to test the utility of automated feature creation, feature selection and algorithm selection & optimization functionalities offered by AutoML tools like H2O driverless AI and DataRobot for credit card loss forecasting • Developed a POC for the model monitoring module of a credit card loan charge-off loss prediction model

Analytics Consultant, Chicago Botanic Garden Feb 2019 – Jun 2019 • Developed a classification model for customer segmentation to inform marketing efforts using supervised techniques • Architected and built an end-to-end ML pipeline including a flask application and deployed the solution in an in-house Windows server

Analytics Consultant, University of Chicago Urban Labs Crime Lab Oct 2018 – Jun 2019 • Explored architectures like GLMs, Neural Networks, Gradient Boosted Trees and ensemble models for modeling the propensity of an individual to be involved in a crime • Helped UChicago Crime Lab validate their own model and identify additional features that may add lift and help improving the accuracy

Business Operations Associate Consultant, ZS Associates Pvt. Ltd. Jul 2015 – Jul 2018 Worked for Fortune 500 pharmaceutical companies across various workstreams such as Salesforce Incentive Compensation Plan Design and Administration, Salesforce Design Optimization, Salesforce Territory Alignment Operations, Customer Targeting and Segmentation, and Specialty Pharmacy Performance Analytics • Led a team of five associates on a large-scale Salesforce Incentive Compensation Operations project; responsible for planning and workload distribution, ensuring quality and timeliness of all deliverables and facilitating all oral and written communication • Successfully led the implementation of new IC plan changes including requirements gathering, implementation planning, POC evaluations, System Integration Testing, User Acceptance Testing and rollout • Reduced cycle time by 75% and substantially improved quality in a Salesforce Territory Alignment Operations project by building an operationally efficient ETL process using SAS and in-house tools • Analyzed transaction level Specialty Pharmacy sales data in SAS and created a dynamic excel dashboard to study and track Key Performance Indicators for Specialty Pharmacies; Information was used by the client for contract renewals • Applied regression modelling to quantify the impact of Salesforce Design change recommendations to maximize YoY sales growth

Academic Projects House price prediction full stack app • Built a completely reproducible and modular machine learning app from proof of concept to production in Python, hosted on AWS EC2 with 82% ML model accuracy and stored customer logs in RDS MySQL database

Handwritten Text Recognition Deep Learning Model • Built a model using CNN and bi-directional LSTM with a Beam Search decoder to recognize text in handwritten text images

Customer Segmentation for a Daily Local Newspaper • Used k-means clustering for customer segmentation to drive personalized recommendations via newsletter for a daily local newspaper

Venmo Transaction Clustering • Developed a clustering solution in Spark to cluster Venmo Transaction data using text based attributes

Achievements • Among Top 4 finalists selected for panel presentation in Data Smackdown organized by ENOVA Feb 2019 • Secured Third place in TEC{H}ACK Hackathon organized by the Boston Consulting Group (BCG) Jan 2019

Alicia Burris (612)-229-0011 • [email protected] • www.linkedin.com/in/aliciaburris • Open to Relocation

Seeking opportunities to leverage a data science academic degree with data engineering skills gained in industry.

EDUCATION Northwestern University, McCormick School of Engineering Evanston, IL Master of Science in Analytics December 2019 • Coursework includes eight month practicum and three month capstone group projects with industry partners

Oberlin College Oberlin, OH Bachelor of Arts in Mathematics, Minor in Hispanic Studies December 2014 • Four year John F. Oberlin Scholarship Recipient; a competitive merit based scholarship

Online Coursework Deep Learning Specialization on Coursera January 2019 • Hyperparameter tuning, Regularization, Optimization, CNNs, ML Project Structures, Sequence Models

TECHNICAL SKILLS • Languages: Java, Python, SQL, R, JavaScript, AngularJS, HTML, CSS, jQuery, JSON, D3 • Frameworks: Spark, Hadoop, Spring MVC, Swagger UI, Pandas, TensorFlow, Hive, HBase • Tools: GCP, AWS, Docker, , IntelliJ, PyCharm, Eclipse, Maven, Git, Postman, Subversion • Modeling Skills: Regression, clustering (k-means, partitioning), classification trees, recommendation systems, KNN, factor analysis, time series, markov chains, survival analysis, principal component analysis

PROFESSIONAL EXPERIENCE Palo Alto Networks Santa Clara, CA Big Data Engineering Intern June - September 2019 • Provided backend support for an on-premise legacy application that is migrating into the cloud. • Developed a RESTful microservice application to expose the running within cloud based containers. • Configured JWT authentication and HTTPS protocols to establish cloud security measures.

Optum Technology Eden Prairie, MN Application Developer March 2015– August 2018 • Built configurable logic for clinical assessment functionality to be leveraged by behavioral health programs. • Automated daily reports on large scales of data to provide recommendations for a member’s plan of care. • Reduced server outages by finding excess web service calls, logging statements, and database transactions. • Optimized costly data refresh logic by identifying 50,000 records with a high likelihood of future activity.

PROJECTS

Blue Cross and Blue Shield of Illinois, Montana, New Mexico, Oklahoma and Texas Student Data Science Consultant October 2018- June 2019 • Built a recommendation system to deliver suggestions to members when searching for in-network providers. • Used clustering and collaborative filtering to serve predictions in real time within a flask web application.

Toddler Screening for Autism Spectrum Disorder (ASD) April 2019- June 2019 • Developed a web application to identify patients with a high risk of ASD hosted in Amazon Web Services.

Ann & Robert H. Lurie Children's Hospital of Chicago Student Data Science Consultant October 2018- May 2019 • Used spinal and chest surgery recovery data to recommend cost reduction strategies for pain management. • Presented findings to the hospital’s director of nursing research.

Predictive Analytics for an online book retailer October 2018- December 2018 • Identified target customers for an advertising campaign and predicted purchase outcomes. Alex J. Burzinski [email protected] • www.linkedin.com/in/alex-burzinski-2a572097 • (920) 366-4710

EDUCATION Northwestern University Evanston, IL Master of Science, Analytics Expected Graduation 12/2019 • Current 3.94 GPA • Relevant Coursework: Predictive Analytics, Python & Java, SQL/Data Warehousing, Business Consulting, Data Mining, Data Visualization, Deep Learning, A/B Testing, Big Data Processing, Text Analytics

University of Wisconsin - Madison Madison, WI Bachelor of Science, Mechanical Engineering Graduated 05/2013 • Dean’s List Every Semester • Graduated with Distinction

TECHNICAL EXPERTISE Python, R, SQL, Java, Hadoop Ecosystem Tools including Hive and Spark, D3.js, Tableau, Git/GitHub, AWS, Azure

PROFESSIONAL EXPERIENCE ENOVA INTERNATIONAL, Chicago, Illinois (06/2019 – 09/2019) An Illinois based financial technology lending company. Portfolio Analytics Intern Responsible for helping the analytics team design and improve efficacy of differing financial products. • Worked with business to understand current product status and possible product improvements • Developed machine learning models to predict loan issue rate and default rate • Worked with analytics team to test models and make sure they meet compliance requirements • Created production version of models to automate scoring of new potential customers on a monthly basis

SKYLINE TECHNOLOGIES, Green Bay, Wisconsin (01/2014 – 08/2018) A Wisconsin based IT consulting company specializing in custom software and business intelligence development. Data Analytics Engineer II Responsible for working to meet the needs of a wide variety of clients of differing sizes and industries, using both waterfall and agile methodologies. • Worked with clients to determine scope and requirement of projects • Worked with both clients and Skyline Associates to design solutions • Worked with clients to test projects and make sure they meet requirements • Promoted projects to production environments and made sure they remained reliable and accessible

FEATURED TECHNICAL PROJECTS

Worked to Maximize the Expected Return on Loan Advertising • Created XGBoost model to predict loan issue likelihood using Python • Created Random Forest model to predict loan default likelihood using Python • Combined results of both models to determine best advertising targets

Predicted the Effectiveness of a Promotional Offer for an Online Retailer • Created a Logistic Model with R to determine the probability of previous customers returning • Used a Linear Model with R to forecast the amount each user would spend during the promotion

Created Sales Reports Consumed by Executives at a Fortune 500 Manufacturing Company • Used SQL to access and transform CRM data and sales data • Built a Data Warehouse to hold the data and scheduled a job, using Python, to update the Data Warehouse daily • Created reports and dashboards for end users to consume using Power BI and Tableau

Ted Carlson 715.577.8851 | [email protected]

EDUCATION Northwestern University Evanston, IL Master of Science in Analytics Expected December 2019 Coursework: Databases, Predictive Analytics, Java and Python Programming

University of Wisconsin - Madison Madison, WI Bachelor of Science in Mathematics and Statistics May 2014 Coursework: Linear Algebra and Differential Equations, Introduction to Programming, Calculus, Introduction to Probability, and Applied Regression Analysis

SKILLS R, Python, Java, SQL, VBA, Git, Excel, Tableau, ArcGIS, LaTeX, Pandas

EXPERIENCE American Family Insurance Madison, WI Reporting Analyst April 2016 - June 2018 ● Created a dashboard in Tableau for our state product directors and sales managers to analyze the performance of our usage-based insurance programs. ● Detected an irregularity in high speed drivers in Utah and Idaho that led to the company adjusting its algorithm to account for states with higher maximum speed limits. ● Assisted with the development of reports used for analyzing the performance of our automotive and property lines of business. ● Eliminated over 40 hours of work per month by automating recurring report processes that were previously done manually.

American Family Insurance Madison, WI Actuarial Analyst May 2014 - April 2016 ● Created territory heat maps using ArcGIS to compare our rates to competitors within each territory and line of business. ● Developed premium calculators which were used to detect multiple errors in our rate-making software by using extreme pricing scenarios. ● Worked on the specialty pricing line to develop recommendations for state pricing strategies.

PROJECTS UPS - Industry Practicum October 2018 - June 2019 ● Working to create a model that can predict the chances a package will be delivered on time using traffic patterns, weather, road closures and route characteristics. ● Determining the impact of large-scale weather events on deliveries before, during and after the event.

Lingjun Chen

[email protected] | 408– 603– 1898 | Github: github.com/Ivanclj

EDUCATION Northwestern University, Evanston, IL September 2018 - December 2019 Master of Science in Analytics GPA: 3.98/4.0 Expected Courses and Topics: Data Mining, Predictive Analytics, Big Data (Hadoop & Spark), Data Visualization (D3.js), Text Analytics, Databases & Data warehousing, A/B testing, Optimization, AWS (S3,RDS,EC2)

Purdue University, West Lafayette, IN August 2014 - May 2018 Bachelor of Science in Mathematics/Statistics & Applied Statistics | Minor: Economics GPA: 3.96/4.0 Awards: Dean’s List & Semester Honor (All Semesters Attended)

EXPERIENCE Data Scientist Intern at LinkedIn, Sunnyvale, CA June 2019 - September 2019 Learning Product Data Science Team • Performed causal inferences on user’s top funnel engagement to their sign-up rate as well as on key on-boarding action drivers to user’s engagement • Obtained causal estimates via Coarsened Exact Matching, Doubly Robust Estimator and Instrumental Variables methods, and presented findings to key business stakeholders to influence product roadmap • Designed experiments to serve as instruments in IV method and worked closely with product managers & engineering team to push experiments to production • Modularized scripts for Data ETL in Spark & Hive, and Causal analysis in R for better usability and generalizability of future causal projects Data Scientist Intern at Ringle.AI, Shenzhen, China May 2018 - August 2018 Stream Recommendation Team • Performed tokenization and TF-IDF as well as tried pre-trained word embeddings to convert over 80,000 parsed article data to vectors and stored results in MongoDB • Implemented multiple unsupervised clustering algorithms to separate all articles into 45 clusters • Solved the system cold-start problem by using article meta data (tags) embeddings to train a KNN and a logistic regression classifier to classify user vector to cluster and return recommended results based on cosine similarity and other covariates • Built a hybrid recommender model with LightFM to recommend articles using both collaborative- filtering method and content-based method Research Assistant at Purdue CLAN Lab, West Lafayette, IN May 2017 - April 2018 CLAN Lab (Cloud Computing, Machine Learning, and Network Research) • Conducted research on using Deep Learning approach to estimate human health metrics (heart rate (HR), HRV) from facial features extracted from videos of subjects • Implemented face detection algorithms such as DeepFace using OpenCV • Constructed a mix model of CNN and LSTM in TensorFlow to classify human stress state (in stress or no stress) using facial features

COMPETITION Purdue Dawn or Doom Cisco Data Dive Competition April 2018 Team Leader • Led the team to win first place out of 50+ teams that participated • Helped Cisco to locate their problems in renewing services by analyzing Cisco’s services data for the last two fiscal years and presented our solution. Our solution projected to help Cisco to increase renewal rate by 15% and to gain an extra 5 million dollars revenue globally • Build a Random Forest and a XGBoost model in R with 92% accuracy in a 10-fold cross- validation to help Cisco forecast future renewal rate SKILLS Programming Language & Software: Python, R, SQL, Spark, Scala, Hive, Java, Flask, Tableau, D3, Git, Bash, AWS Machine Learning & Analytics: • Predictive modeling (Logistic Regression, Random Forest, Boosting Tree, SVM), Clustering, Neural Network, Deep Learning, A/B Testing, Experiment Design, Bayesian Inferences, Time Series Analysis

Si (Angela) Chen [email protected] · www.linkedin.com/in/angela-chen-nu· (847) 909-3198 · https://github.com/Cris7777 ​ ​ ​ ​ ​ ​

EDUCATION Northwestern University (NU), Evanston, IL Sep 2018 – Dec 2019 (expected) ​ Master of Science in Analytics GPA: 3.85/4.00 ​ • Related coursework: Predictive Analytics, Data Mining, Data Visualization, Deep Learning, Data Warehousing, Text Analytics, Social Network Analysis Beijing University of Posts and Telecommunications (BUPT), Beijing, China Sep 2014 – June 2018 ​ Bachelor of Management in Information Management and Information Systems GPA: 3.95/4.00 ​ • Awarded First Prize Scholarship for academic excellence in 2015, 2016 and 2017 TECHNICAL SKILLS • Programming: Python, R, SQL, Java, C, D3.js, MDX, XML, HTML5 ​ • Tools & Systems: Hadoop, Spark, Tableau, Git, Bash, AWS, Hbase, Hive, Visual Studio, StreamBase Studio, Jupyter Notebook, Latex, Cloud Platform • Skills: Predictive Modeling, Clustering, Time Series Analysis, A/B Testing, Experiment Design ​ WORK EXPERIENCES Lyft, Boston, MA June 2019 – Sep 2019 ​ Data Scientist Intern, Lyft Bike & Scooter - Science • Quantified impact of over 150,000 docking errors on fleet availability by understanding customer and technician behaviors on rendering the bike as unavailable in different circumstances • Broken down missing bikes during rental to different causes for reducing 300 monthly fraudulent rentals • Applied K-Means algorithm in Python to classify over 400 bike stations into three categories based on the duration of emptiness or fullness, combined with departure and arrival rate to develop hourly valet strategies • Self-defined mean minutes between work orders to measure the quality of a repair, distinguished bikes with low metric values and marked mechanics with high rates in fixing problematic bikes • Cooperated with other data scientists and market managers to improve the ride ability around Boston area ABC Supply, Evanston, IL Nov 2018 – June 2019 ​ Student Analytics Consultant • Classified products into four categories based on the variability in monthly demand timing and demand quantity • Built time series models in R to predict sales demand of products making up 80% of revenue, calculated weighted mean absolute percentage error in nested cross validation to select the best model for each product • Predicted product demand three months ahead with selected models, designed a dashboard in Tableau reflecting demand trend and demand prediction by region and product type Amazon, Beijing, China Mar 2017 – Jan 2018 ​ ​ ​ BI Analyst Intern, Supply Chain Execution • Discovered statistical advantages of daily operations with EDI by comparing operating metrics of over 800 vendors in SQL to help Amazon Dropship transition from non-EDI vendors to EDI vendors • Used Json to create endpoints and configure relationships of EDI, tested transfer feasibility and accuracy of EDI message enveloped in XML through SFTP • Collaborated with vendor managers and DevOps engineers to conduct integration tasks for vendors PROJECT EXPERIENCES Web APP on Predicting Soccer Player Class, NU, Evanston, IL Apr 2019 – June 2019 ​ • Pre-processed and cleaned data, extracted features and labels, trained and selected model in Python • Constructed and connected EC2 instance, S3 bucket and RDS database in AWS for data upload and storage, created and linked pages with HTML to provide a website on predicting the athletic level of a soccer player • Automated the reproduction process with Makefile, Yaml and Args Analysis on Domestic Bitcoin Market, BUPT, Beijing, China May 2016 – June 2017 ​ ​ ​ • Utilized stationary test and cointegration test to prove that variables on domestic bitcoin market are correlated • Investigated qualitative and quantitative relationships between domestic bitcoin trading volume and its influencing factors through granger causality test and regression analysis Zijin ‘Carson’ Chen [email protected] EDUCATION Northwestern University McCormick School of Engineering Evanston, IL Master of Science in Analytics Expected Graduation: December 2019 . Course topics: machine learning, data mining, databases, big data, NLP, deep learning, data visualization . Future coursework: reinforcement learning, text analytics, business value from analytics

Macalester College St. Paul, MN Bachelor of Arts in Applied Mathematics and Statistics, Economics, summa cum laude 2011 – 2015 . Recipient of Kofi Annan Scholarship and 2 economics department prizes, GPA 3.91/4.00

TECHNICAL SKILLS Programming: Python (pandas, scikit-learn, pySpark), R (dplyr, ggplot2), Java (MapReduce), Javascript (D3.js) Tools: SQL (Presto, Hive), Hadoop, Git, Bash, AWS (EC2, RDS, S3), Tableau, Stata, ArcGIS, Office

PROFESSIONAL EXPERIENCE LinkedIn Sunnyvale, CA Data Science, Analytics Intern June 2019 – September 2019 . Conducted data deep dive using R with Presto/Hive SQL queries to uncover predictive signals of fraudulent and abusive accounts, in order to reduce their damage metrics to the network . Identified major fraud types using TF-IDF method on text data and provided actionable feature recommendations to substantiate anti-abuse ML model and improve its recall and response time . Scheduled scripts for automatic data ETL in Azkaban in order to monitor evolving fraud patterns

Chicago Botanic Garden Evanston, IL Student Data Science Consultant January 2019 – June 2019 . Delivered a machine learning empowered app solution using python-Flask to categorize the entire database of current customers into distinct lifetime value buckets, and expandable to new customers . Incorporated findings from a comprehensive survey as training label, and implemented supervised learning methods (XGBoost, random forest) to make prediction on not-in-survey customers, and achieved significant lift of offline cross-validated prediction accuracy from baseline . Served as the main liaison with the client to manage project workflow and communications

Zurich North America Insurance Evanston, IL Student Data Science Consultant October 2018 – June 2019 . Performed comprehensive exploratory analyses and data cleansing on risk assessment records and insurance claim history, and developed systematic steps to merge the data, including fuzzy matching . Employed GLM framework with standardization in R to create predictive models on claims

Economists Incorporated San Francisco, CA / Washington, DC Economic Consulting Analyst / Research Associate June 2015 – June 2018 . Performed rigorous research and statistical analysis to aid economists testify for legal cases, and substantiated rebuttals by replicating opponents’ analysis to identify contrary evidence . Examined the gigabytes of structured and unstructured datasets to answer key questions, synthesize insights, make inferences, and construct compelling narratives from the data . Translated technical results into figures and illustrations intended for non-technical audiences . Worked on 10+ cases for a variety of industries and functions, selected examples include: o Built automated reporting tool in Stata to assess monopoly power of hospitals in regional markets o Conducted econometric analysis to quantify wage discrimination in packaging factories o Maintained and improved electricity marginal pricing models in Excel for utility providers

PROJECTS ACE.AI ATP Tennis Match Predictor (available on GitHub) . Designed the interactive python-Flask app to make tennis match predictions using XGBoost model . Built reproducible scripts end-to-end from data retrieval to UI, and hosted the app with AWS EC2 Harish Chockalingam Cell phone: 847-800-8158 Email: hchockalingam@.com

Education M.S Analytics, Northwestern University Anticipated: December 2019 M.S Mechanical Engineering, Northwestern University June 2018 B.S Bioengineering with Mathematics Minor, University of Illinois at Chicago May 2013

Programming Skills Python, C, R, MATLAB, JAVA, GitHub, MS Visual Studio

Engineering and Design Skills Solidworks, Rapid Prototyping, Statistical Analysis, Design of Experiments

Relevant Coursework Embedded Systems in Robotics, Mechatronics, Statistics, Linear Algebra, Engineering Optimization

Graduate Research Estimation of needle deflection and tissue deformation for improving target accuracy of biopsy procedures using Digital Image Correlation

Work Experience Fresenius Kabi Melrose Park, IL Associate Project Engineer January 2018 - August 2018

• Supported Metler Toledo control systems and database for serialization of pharmaceutical Packaging • Initiated and executed engineer change request (ECR) for equipment setup and operation • Identified bottlenecks to production OEE data; provided recommendations to management as part of continuous improvement effort to increase output, efficiency, and quality • Educated operators on serialization and enforced good manufacturing practice (GMP)

Hospira – Pfizer Company Lake Forest, IL Product Development Test Engineer, Consumables R&D August 2014 - November 2015

• Performed feasibility studies and testing for test method validation in a lab setting • Collaborated with design engineer to develop Test Methods for drop testing of packaged devices • Conducted flow rate testing, pressure leak testing, tensile testing, and force testing of medical devices as per ISO acceptance criteria and design inputs while following GDP and GLP • Analyzed data from testing for premarket approval document, 510k

Corptax, Inc Deerfield, IL Associate QA Engineer I November 2013 - August 2014

• Conducted manual regression testing on company’s tax software for quality before cycle release • Coded test cases to exercise software using Action Based Testing (ABT) • Analyzed KPI of test case from daily ABT runs to improve overall functionality of the software • Tested bugs reported by clients to ensure quality and integrity of the system • Prioritized tasks needed to be completed on a sprint basis in SCRUM meetings

Sabarish Chockalingam E-mail: [email protected] Cell: 847-800-8094 Linkedin: http://www.linkedin.com/in/sabarishchockalingam/

EDUCATION Northwestern University, Evanston, IL Anticipating Graduation: Dec. 2019 Master of Science in Analytics Candidate Expected Course Completion: Predictive Analytics, Data Mining, Data Visualization, Analytics for Big Data, Deep Learning, Text Analytics

Northwestern University, Evanston, IL Mar. 2018 Master of Science in Mechanical Engineering Cumulative GPA: 3.81/4.00

University of Illinois, Chicago, IL May, 2013 Bachelor of Science in Bioengineering, Minor in Mathematics Cumulative GPA: 3.88/4.00 Affiliations: Tau Beta Pi Engineering Honor Society Zeta Chapter (as Fundraising Chair), Alpha Eta Mu Beta National Biomedical Engineering Honor Society, UIC Honors College

SKILLS Programming and Computer Applications: Python, R, SQL, Java, MATLAB, C/C++, , Mathematica, ABAQUS, ANSYS, Adobe Photoshop & Illustrator

Quality Assurance: documentation, change control, creating project schedules, FMEA, CAPA

Design and Manufacturing: AutoCAD, Eagle CAD, Siemens NX, CNC Machining (HAAS), 3D printing, laser cutting, injection molding, embedded computing (Microchip PIC)

PROFESSIONAL EXPERIENCE Abbott Diagnostics Division, Lake County, IL Nov. 2014 – Dec. 2016 Validation Engineer II ● Authored electronic test documents in Laboratory Information Management System (LIMS) to perform calculations and evaluate test data from diagnostic instruments. ● Simulated in LIMS to validate electronic test documents. ● Authored testing documents in accordance with on-market design control specifications subsequently used to release product for sale.

Wockhardt – Morton Grove Pharm., Morton Grove, IL May 2014 – Nov. 2014 Packaging Development Associate ● Updated packaging component specifications to current manufacturer specifications. ● Prepared change control documentation and communicated for approval of updates.

RESEARCH AND PROJECT EXPERIENCE Peltier Personal Cooling System (PCS), Northwestern University Jun. 2017 – Sep. 2017 Masters Project ● Designed and assembled PCS that uses Peltier effect (which uses fewer moving parts compared to a vapor- compression cycle PCS). ● Proposed design requirements for soldier needs during deployment in hot environments and ASHRAE thermal comfort standards in mind.

Laboratory of Product and Process Design, UIC, IL Jan. 2012 – May 2012 Undergraduate Research Assistant ● Simulated Aquaporin 4 Chemical reaction network via deterministic and stochastic models (increasing Aquaporin 4 concentration is a potential cure for Hydrocephalus.) ● Programmed and simulated Aquaporin 4 models in MATLAB. Helped troubleshoot team members’ code.

Anthony Colucci

2706 N Wayne Ave Apt. 2, Chicago, IL 60614 | 989-397-5714 | [email protected] Education MASTER OF SCIENCE | NORTHWESTERN UNIVERSITY | EVANSTON, IL | SEP 2018 – DEC 2019 (EXPECTED) Major: Analytics Relevant Coursework: Predictive Analytics, Data Mining, Data Visualization, Analytics for Big Data, Deep Learning, Text Analytics, Social Network Analysis BACHELOR OF ARTS | NORTHWESTERN UNIVERSITY | EVANSTON, IL | SEP 2010 – JUN 2014 Majors: Mathematics, Economics, Mathematical Methods in the Social Sciences Relevant Coursework: Probability and Statistics, Econometrics, Game Theory, Real Analysis, Abstract Algebra, Intro to Computer Programming, Corporate Finance Work Experience FRAUD ANALYTICS INTERN | ENOVA | CHICAGO, IL | JUN 2019 – SEP 2019 • Developed a gradient boosted tree model to identify customer accounts that had been taken over by fraudsters using the XGBoost package in Python, significantly lowering the amount of time needed to investigate these cases of fraud • Rewrote the ETL from the organization’s relational database to the Neo4J GraphDB instance allowing for more use cases of social network analysis in fraud investigations TECHNICAL SERVICES ANALYST | EPIC SYSTEMS | VERONA, WI | OCT 2014 – MAY 2017 • Led three customer teams to resolve technical issues within their systems and implement software upgrades and optimization projects Projects INDUSTRY PRACTICUM | UNIVERSITY OF CHICAGO CRIME LAB | SEP 2018 – JUN 2019 • Created a data pipeline and predictive model using the XGBoost package in R to identify individuals most at risk for involvement in gun violence, outperforming existing models over a validation sample DEEP LEARNING PROJECT – ALBUM-AI.HEROKUAPP.COM | APR 2019 – JUN 2019 • Fit a convolutional neural network using the Keras and Tensorflow packages over a dataset of album cover art in order to predict the genre of the music played on the album SPORTS STATISTICS PROJECT – GITHUB.COM/TONYCOLUCCI/AVC_PROJECT | APR 2019 – JUN 2019 • Created a Flask application to make a model-based prediction about the likelihood of success of a frisbee throw based off of data from the 2017 USA Ultimate season • Persisted a database of throws for training and predicted values using S3, EC2 and RDS services on AWS Technologies • Python: Professional and academic experience using base Python and accessory packages, including pandas, sklearn, XGBoost, statsmodels, flask, sqlalchemy and matplotlib • R: Professional and academic experience using base R and a range of packages, including the tidyverse suite, dplyr, ggplot2 and tidygraph • SQL: Professional and academic experience writing complex queries using multiple dialects including MySQL, Microsoft SQL Server and PostgreSQL

JD COOK [email protected] | www.cookjoseph.com | github.com/josephd8

EDUCATION Northwestern University September 2018 – December 2019 Masters in Analytics Evanston, IL Coursework: Machine Learning, Deep Learning, Big Data, Data Mining, Production-Level Programming, Text Analytics, Network Analytics, Data Visualization, Databases, Analytical Consulting

Brigham Young University – Presidential Scholarship April 2018 Bachelor of Science in Statistics, Emphasis in Applied Statistics and Analytics Provo, UT Social Innovation Leadership Council

TECHNICAL SKILLS Data Science: R, Python, SQL, RShiny, Flask, Spark, MapReduce, Hadoop, Hive/HBase, Tableau, D3.js Web & Back End: HTML, CSS, JavaScript, Java, C++, Node.js, AngularJS, MongoDB Other: Bash, Git, AWS, Google Cloud, A/B Testing

EXPERIENCE AeroPay – Product Manager January 2019 – September 2019 ▪ Leading outcome-based product roadmap and strategy for 3 products (2 mobile + 1 web) ▪ Built and deployed custom company-wide KPI dashboard from scratch using R/RShiny ▪ Developed production Python code automating detection of fund-transfer failures ▪ Conducting qualitative research with users; driving product discovery and feedback loop

Principal Financial Group – Data Science Consultant September 2018 – June 2019 ▪ Employed nonlinear optimization methods to perform automated portfolio construction based on targets ▪ Delivered full web-application to enable managers to construct, optimize, test, and share portfolios

Qualtrics – Data Scientist September 2016 – August 2018 ▪ Managed >$700k in product research projects for >75 clients, including Fortune 500 companies ▪ Developed and maintained R packages to automate analysis process; reduced project time by >50% ▪ Validated and delivered back-end estimation model in PyStan for Qualtrics Conjoint Module

PROJECTS & HACKATHONS Album.AI – Deep learning + computer vision to classify genre by album artwork March 2019 – June 2019 Developed convolutional neural network (VGG) and combined with pre-trained object detector (Mask- RCNN) to classify album genre based on based on album artwork. Configured and managed Google Cloud servers with custom GPU for model training.

Kittyfarm – Cryptokitty value predictor for beginner cryptokitty owners March 2019 – June 2019 Extracted and parsed data on ~1.6 million kitties using Cryptokitties API. Used gradient-boosted trees (scikit-learn) to predict any live kitty’s value in the market. Built full Flask app and deployed using AWS.

ABC Supply Hackathon – 1st Place (23 teams of Masters students) May 2019 Engineered features of branch credit performance using dimension reduction & k-means clustering. Built 3- D visualizations using Plot.ly. Presented to ABC Supply Data Science Leadership.

Qualtrics Hackathon – 2nd Place company-wide (only “non-engineer” to participate) May 2018 Designed and prototyped a profit-optimizer for choice-based product experiments using RShiny. Presented to Qualtrics Executive Team. Partnered with PM and engineers to begin further adoption into software.

CHUAN (SOPHIE) DU +1 (217) 417-8936 | [email protected] | https://www.linkedin.com/in/chuan-sophie-du/

EDUCATION NORTHWESTERN UNIVERSITY EVANSTON, IL Master of Science in Analytics EXPECTED: SEP 2018 - DEC 2019 UNIVERSITY OF ILLINOIS AT URBANA – CHAMPAIGN URBANA – CHAMPAIGN, IL Bachelor of Science in Applied Mathematics, Statistics; Minor in Informatics, Computational Science & Engineering AUG 2014 – MAY 2018 ▪ Graduated with High Distinctions, LAS Dean’s List, Pi Mu Epsilon National Mathematics Honor Society ▪ Meritorious Winner of 2017 the Mathematical Contest in Modeling (MCM)

SKILLS ▪ Data Science: Predictive Analytics, Data Mining, Text Analytics, Big Data Analytics, Data Visualization, Data Warehousing, Deep Learning, Machine Learning, Optimization ▪ Programming & Software: Python, R, SQL, SAS, LaTeX, AWS RDS, Tableau

EXPERIENCE OPEX ANALYTICS – SOLUTIONS TEAM CHICAGO, IL Data Scientist Intern JUN 2019 – PRESENT ▪ Deploying descriptive, predictive and prescriptive analytics contingency solutions to identify and reduce global trade flow risks for Top 25 world supply chain based on third party provided tariff data ▪ Performed tokenization and lexicon normalization such as stemming and lemmatization; Generated features with TF-IDF to convert over 170,000 tariff control text data to vectors; Conducted sentiment analysis using text classification, with random forest, logistic regression and SVM classifiers to classify control relevance with client’s trade flows ▪ Automated pipeline of extracting and concatenating dynamic unorganized data for each extracts type and modify date as well as merging weekly updated information into master file with changes labeled

ILLINOIS GEOMETRY LABORATORY – DISCRETE MORSE THEORY & VECTOR FIELDS CHAMPAIGN, IL Undergraduate Researcher JAN 2016 – FEB 2018 ▪ Publication: RGB image-based data analysis via discrete Morse theory and persistent homology, (first author) with C. Szul, A. Manawa, N. Rasekh, R. Guzman, R. Davidson, arXiv:1801.09530 ▪ Designed converters using Python to convert RGB images into grayscale, used Australian National University’s source code to create discrete Morse functions (DMF) to extract key topological information from images, and constructed custom models of DMF vector fields in a cubical complex ▪ Generated data-informative persistence diagrams to describe the birth and death time of persistence pairs, enabling users to predict future image-based data behavior with the life-span information of topological features in the input images ▪ Applied the theory to perform analysis on open-source heat maps of water scarcity variability and crime rates variability data

BP NORTH AMERICA – INDUSTRY PRACTICUM AT NORTHWESTERN UNIVERSITY EVANSTON, IL Data Science Student Consultant NOV 2018 – JUN 2019 ▪ Developed recommendations for BP regarding periodic product pricing based on similar competitor comparisons. Produced models to forecast and explain monthly profiles and various time series data. ▪ Predicted probabilities of winning a bid given current market conditions and contracts’ specifications, with accuracy of 85.7%. ▪ Translated calculations performed in Excel workbooks into PySpark to be operated in BP’s Palantir cloud environment

FUNCTION CAPITAL – SILICON VALLEY OFFICE REDWOOD CITY, CA Investment Analyst Summer Intern JUN 2017 – JUL 2017 ▪ Conducted industry research on target projects in fields of machine learning and robotics for investment decision-making including initial financing investigation and competitiveness analysis

CHINESE ACADEMY OF SCIENCES – INSTITUTE OF COMPUTING TECHNOLOGY BEIJING, CHINA Research Assistant AUG 2017 ▪ Constructed mathematical models and developed random walk algorithm for microRNA-disease associations using Python based on integrated similarities of Gaussian interaction profile kernel similarity, semantic similarity and functional similarity

COMPETITION & PROJECT WAITING IN AIRPORT SECURITY CHECKPOINT: A PERSPECTIVE FROM QUEUEING THEORY – 2017 MCM/ICM JAN 2017 ▪ Led the group to conduct empirical analysis using R to establish a mathematical model for increasing checkpoint throughput and reducing variance in wait time; Developed two modifications to the current procedural model, with the first one incorporating a Bifurcation System and the second designing a Circular Line-up System

WEB APP DEVELOPMENT: USED CAR PRICE PREDICTOR – NORTHWESTERN UNIVERSITY MAR 2019 – JUN 2019 ▪ Developed a Flask web app with Python for predicting car prices based on user input of car features, with accuracy of 87% Ruixiang (James) Fan www.linkedin.com/in/ruixiang-james-fan | (925) 566-4251 | [email protected] EDUCATION Northwestern University, Evanston, IL Expected Dec 2019 Master of Science in Analytics (MSiA) • Coursework: Database and Information Retrieval, Predictive Analytics, Data Mining, Big Data, Data Visualization, Deep Learning University of California, Los Angeles, Los Angeles, CA Jun 2016 Bachelor of Science in Mathematics/Economics, Magna Cum Laude • GPA: Cumulative GPA: 3.89/4.0, Major Upper Division Courses GPA: 3.97/4.0 TECHNICAL SKILLS AND CERTIFICATIONS Programming & Software: R, SQL, Python, MicroStrategy, Git, JavaScript (D3) Certifications: Society of Actuaries Exam Probability, Society of Actuaries Exam Financial Mathematics Languages: English (fluent), Mandarin (native) PROFESSIONAL EXPERIENCE Crate and Barrel, Northbrook, IL Jun 2019 - Aug 2019 Data Analyst Intern • Generated text classification model with Python on low-rate online reviews to raise the efficiency of team-disposition and problem-solving process, saving merchandise team 10 hours a week • Developed visualizations and time series analytics on specials orders to reduce lead time and costs • Conducted correlation and regression analysis to understand the impact of key macroeconomics variables on sales performance BP North America, Northwestern University Oct 2018 - Jun 2019 Analytics Student Consultant • Developed automated regional pricing dashboards with PySpark in AWS environment to provide recommendations on implementing unbranded oil, highly valued and adopted for long term use Brookhurst Insurance Services, Los Angeles, CA Oct 2016 - Jul 2018 Data Analyst • Initialized reorganization and migration of company’s database from Excel files to Salesforce and SQL for better completeness and efficiency, increasing renewal ratio by 15% • Generated clusters to reasonably distribute clients, increasing sales by 11% • Managed planning and development of procedure for weekly and monthly metric reports • Self-learned Apex in two months and received promotion to main Salesforce developer • Led weekly 30-person sales meeting to motivate callers, augmenting calls by 100 /person /week Huanyu Consulting and Accounting Company, Dalian, China Jul - Sept 2015 Data Analyst Intern • Collaborated with a team of 5 in collecting and analyzing data of properties assessment, aced the project and established long-term cooperation with government • Proposed notification process to IT department solutions for enhancing system efficiency PROJECT EXPERIENCE Analytics Value Chain, Northwestern University Apr - Jun 2019 • Developed web app with AWS to understand the impact of house features and to predict final prices BuildChange Extracurricular Project, Evanston, IL Jan - Jun 2019 • Built in the required structural criteria into the module classified data sets in R for training purposes Kaggle Competition - Elo Merchant Category Recommendation, Evanston, IL Jan - Mar 2019 • Implemented gradient boosted tree, and random forest to help understand customer loyalty INTERESTS Basketball, Soccer, Tennis, Billiard, Piano, Chinese Chess, Reading, Murder Mystery Games S. MICHAEL FEDELL github.com/michaelfedell | [email protected] | michaelfedell.com Education Northwestern University | Evanston, IL Sep 2018 - Dec 2019 Master of Science in Analytics (MSiA) Cumulative GPA: 3.98 University of Oklahoma | Norman, OK Aug 2014 - May 2018 B.S. Chemical Engineering, Minor in Spanish Cumulative GPA: 3.95 Professional Experience NASA Jet Propulsion Laboratory - Data Science / ML Engineering Intern Jun 2019 - Sep 2019 Worked in the Office of the Chief Innovation Officer to build machine learning pipelines for numerous data science projects focusing on anomaly detection in time series streams. Coordinated work with internal mission teams and external client who provided operations telemetry for analysis. Leveraged GPU's and high performance computing systems and optimized algorithms to reduce experimentation time by 60%. Deployed common framework and reporting system to monitor live experiments and track results. BP North America - MSiA Practicum Engagement Oct 2018 - Jun 2019 Designed a data pipeline and suite of predictive analytics tools to assess regional risk for commercial contracts as well as a comprehensive pricing analysis dashboard for the Planning and Optimization teams at BP. Oseberg, Oklahoma City - Data Analytics Intern Jun 2018 - Sep 2018 Developed a User Health Model based on 30 features across two thousand users to help guide customer retention teams and prevent churn. Stood up an automated ETL and weekly reporting system to deploy and deliver results. Led a data engineering project to onboard new data vendor. Published several python libraries for sustained use. Irani Center for Creation of Economic Wealth (I-CCEW) Nov 2017 - May 2018 Software Business – Software Developer Worked with team of 4 developers and 4 business analysts to create software solutions for small businesses and local entrepreneurs. Delivered a complete e-commerce platform custom-built from scratch for a large manufacturer. Relevant Skills and Coursework Data Mining, Analytics for Big Data, Cloud Computing, Deep Learning, Data Visualization, Reinforcement Learning, Text Analytics, Predictive Analytics, Databases, Analytics Consulting - Graduate Coursework MEAN.js Full-Stack Web Development (mongo, express, , node) - I-CCEW Development Bootcamp Favored Languages: Python, R, Java, HTML/CSS, Javascript, SQL, C++, C Frameworks: Spark, Scikit-Learn, Flask, Hadoop, FastAI, Torch, Plotly, D3.js, React, Material UI Other Skills: Linux, Docker, AWS, Mixpanel, ElasticSearch, Tableau, Information Retrieval Academic Projects Player Profiling in Just Cause 2 [Gaming Analytics, Behavior Profiling, Churn Prediction, Research] Explored novel algorithms such as Bipartite Tensor Factorization for analyzing spatio-temporal player behavior in open world games. Results provided semi-autonomous feature extraction to improve on profiling and retention. Developed work with team of international researchers and presented results to various conferences/journals. Album AI [Computer Vision, Deep Learning, Web Application, Music Classification] Developed convolutional neural network models to predict music genre based on an album’s cover art. Deployed web application to serve predictions and collect human guesses for benchmarking models. InstaCart Profiler [Cloud Computing, Ensemble Modeling, Cloud Computing, AWS, Model Deployment] Combined various modeling techniques (Clustering, Archetype Analysis, Linear SVM, PCA) to extract and predict order archetypes from the InstaCart dataset. Built an interactive web application around these models and deployed in the cloud using AWS resources. Project emphasizes modularity and model reproducibility. Honors and Awards • Gallogly College of Engineering’s Outstanding Senior • PE-ET 2018 Honor Society for Top 10 Seniors • Eagle Scout - Highest honor in the Boy Scouts of America program • Tau Beta Pi Engineering Honor Society - Top 8% of Engineering Yi (Joyce) Feng [email protected] | 404-433-0432 EDUCATION Northwestern University Evanston, IL • Master of Science in Analytics 09/2018 – 12/2019 • GPA: 3.98/4.0 Georgia Institute of Technology Atlanta, GA • Bachelor of Science in Industrial Engineering 08/2012 – 05/2016 • GPA: 3.85/4.0

WORK EXPERIENCES PayPal Inc. San Jose, CA Data Science Intern 06/2019 – 09/2019 • Constructed an optimized database containing targeted information; performed geo-statistics and clustering analysis with 18M+ records of fraudulent transactions data to identify hotspots in Python • Built predictors with the results from geo-analysis that was capable of improving the true negative rate of current fraudulent prediction performance by ~10% • Worked with a production team to integrate the new predictors and algorithm into current onboarding model American Airlines Dallas, TX Revenue Management Analyst 07/2016 – 07/2018 • Monitored the European and Pacific market performance; interacted with market demands forecasting model and revenue optimization system; improved the revenue performance of markets by ~15% • Developed strategies and took responsibilities of revenue performances in China markets, which generated $200M+ revenue annually • Collaborated with the pricing, operation research and sales teams to develop new data analytics tools and streamlined business processes and strategies PROJECTS What-if Analysis Portfolio Construction – Principal Financial Group 10/2018 – 06/2019 • Closely worked with the portfolio managers at Principal to design and build the portfolio construction tool in R- Shiny as a way to systemize the portfolio construction process • Designed the optimization algorithm that minimized the differences between target and actual portfolios under the constrains set by clients • Helped clients to implement the tool inhouse with detailed technical guide and stepwise user guide Image Process with TensorFlow Autoencoder – Northwestern University 03/2019 – 06/2019 • Collected and removed noises from the background of pictures data with web scrapping and API • Built a deep learning autoencoder model capable of extracting the features from pictures and matching the most similar item from database with the user’s input; loss of the model decreased by 73.33% • Presented final model and project poster at the Analytics Exchange annual data science conference

Fraudulent Booking Prevention – American Airlines 02/2018 – 07/2018 • Used SQL to build a report to monitor suspicious bookings and agencies’ malpractices, which affected over $1M+ annual revenue in Pacific markets • Developed preventive strategies and worked with pricing, revenue integrity and operation research team on market implementation • Successfully decreased fraudulent bookings by 20%+ Inventory Planning for Clothing Company – Georgia Tech 01/2016 – 05/2016 • Developed an inventory planning system with 1M+ sales data records to optimize the inventory turnover ratio and increase profit • Utilized Fourier Analysis and Croston Analysis to forecast demands of 15 active styles, and SKU ratio analysis to allocate demands to color, size and fit SKILLS • Programming: Java, Python, R, SQL, XML, Hadoop, PySpark, D3.js • Data Analysis: Deep Learning, Database Engineering, Statistics, Probability, Optimization, Regression & Correlation, Data Input/Manipulation, Stochastics, Linear Programing, Simulation, Supply Chain Management • Software: Teradata, Jupyter Notebook, Git, Tableau, Minitab, Xpress, ExpertFit, Excel, Simio, SAS • Language: English (Fluent), Mandarin Chinese (Native), Cantonese (Intermediate), Korean (Intermediate) Nathan Franklin [email protected] • 901.871.7671 • https://www.linkedin.com/in/NathanAriFranklin/ EDUCATION Northwestern University, McCormick School of Engineering Expected Graduation Dec 2019 Master of Science in Analytics (Merit-based Fellowship) Evanston, IL Coursework: Relational Databases & SQL, Supervised Learning I & II, Java & Python, Data Mining/ Unsupervised Learning, Data Visualization with D3, Analytics Value Chain, Big Data Tools & Techniques, Deep Learning, Reinforcement Learning in-progress, Optimization & Heuristics in-progress Pomona College May 2016 Bachelor of Arts in Economics (3.71/4.0 Cumulative GPA) Claremont, CA

TECHNICAL SKILLS & PROJECTS Skills: Python • R • Java • SQL • AWS/GCP • sklearn • Spark • Keras • Hadoop • Git

Book Genre Classification Machine Learning Web App Mar - Jun 2019 • Master’s program project - built an interactive machine learning web app deployed on AWS • Used NLP techniques to develop a genre classification model based on user-input book summaries UPS - Master’s Program Industry Partner Project Sep 2018 - Jun 2019 • Worked on novel machine learning approaches to existing organizational last-mile delivery problems Academic Research Project: Gaming Analytics Jan 2019 - Present • In-game Behavioral Profiling & Retention Prediction of players in the video game Just Cause 2 • Submitted paper to 2020 IAAI Conference for Innovative Applications of

EXPERIENCE & INTERESTS United Parcel Service (UPS) - Advanced Technology Group Jun - Sep 2019 Data Science Intern Atlanta, GA • Worked on forward thinking solutions to UPS last-mile package delivery operations tying together multiple disparate UPS data sources as well as 3rd party contemporaneous data sources • Constructed visualizations of insights and findings to present to a UPS data science team & management Southern Growth Studio Dec 2017 - Apr 2018 Management Consulting Intern Memphis, TN • Conducted deep dive industry interviews, organized responses, and helped formulate strategic marketing and business strategy advice for Fortune 1000 as well as local clients • Led intern group on a major Memphis museum project, including brainstorming for a revamping of building grounds, creating a feasible business plan, and outlining a presentation for Memphis City Council Metronome Partners LLC Oct 2016 - Mar 2017 Investment Banking Analyst Intern Memphis, TN • Spearheaded research on middle market clients ranging from 10 to 400 million dollars in yearly revenue • Assisted in creation of pitch books focusing on industry landscape, working with upper level management Interests: NBA analytics, E-sports analytics, 100 hours volunteering @ St. Jude Children’s Hospital, hackathons, low level programming/retro video game emulation Tian Fu 858-766-8334 [email protected] linkedin.com/in/tian-fu tian-fu.squarespace.com | | | EDUCATION Northwestern University Chicago, IL Master of Science in Analytics; GPA: 4.00/4.00 Expected Dec 2019 Relevant Coursework: Predictive Analytics, Databases & Information Retrieval, Python & Java, Data Mining, Data Visualization, Big Data Analytics, Deep Learning, A/B Testing, Data Warehouse, Social Network Analytics, Text Analytics, Leadership Insights & Skills for DS Activity: 2019 Enova International Data Smackdown Finalists

University of California, San Diego San Diego, CA Bachelor of Science in Mathematics (Applied), Bachelor of Art in Economics; GPA: 3.94/4.00 Sep 2014 - Dec 2017 Honors: Summa Cum Laude, Provost Honors, Membership of the Caledonian Society for outstanding seniors Relevant Coursework: Econometrics, Stochastic Processes, Numerical Analysis, Statistics, Operations Research, Actuarial Mathematics SKILLS Technical Skills: Python (Pandas, Numpy, Matplotlib, Seaborn, Scikit-Learn, NetworkX), SQL (PostgreSQL, MySQL, Teradata), R (tidyverse, • dplyr, ggplot, caret), Java, JavaScript (D3.js), Tableau, Matlab, Stata, LaTeX Languages: Chinese Mandarin (Native), English (Fluent), Korean (Basic) • EXPERIENCE Blue Cross and Blue Shield of Illinois Chicago, IL Data Science Intern, Enterprise Data Science Jun 2019 - Aug 2019 Engaged with cross-functional teams to execute business ideas; researched and scoped data science opportunities in claim overpayment ◦ recovery and opioid intervention from both member’s and provider’s perspectives Communicated with clients to refine the scope of opioid abuse problem after reviewing 3000+ lines of SQL codes and understanding ◦ the current work progress; prioritized agile project workflow to meet client needs Visualized targeted members through network analysis based on similarity in prescriptions and demographics to assess the validity of ◦ current definition of opioid abuse, and initiated team discussions to clarify target variable and target population Drove agile product development with a team of two data scientists, and leveraged machine learning and healthcare expertise within ◦ the team to execute the business goal of identifying members at risk to opioid abuse and developing stratified intervention programs

TransUnion Chicago, IL Data Science Consultant Oct 2018 - Jun 2019 Brainstormed and engineered 45+ features using edge classification on 15M+ pairs of consumers based on their demographic and ◦ credit information across 9 datasets Trained logistic regression, random forest, and XGBoost models in R to classify households with the fine-tuned XGBoost model ◦ achieving a KS of 0.9 and increasing household capture rate by approximately 14% Developed matrix representations of pairwise consumer relationships and reinvented household classification approach through ◦ convolutional neural network Designed, implemented and validated household aggregation algorithms in Python to expand traditional definition of household, which ◦ is same last name and same primary address, and offered new targeting opportunities in business areas such as digital marketing

Grid Dynamics International, Inc. San Ramon, CA Accounting Assistant Jan 2018 - May 2018 Managed forecast utility payments for corporate apartments and investigated overpaid benefits payments in Excel; communicated with ◦ benefits specialist to help company obtain $12,000 refund Collaborated with co-workers and vendors on a daily basis to collect and process financial data via QuickBooks, Bill.com and Excel to ◦ avoid delayed payments and misapplied transactions PROJECTS

Bank Customer Churn Evaluation: https://github.com/tiannfff/msia423-final-project • Predicted customer churn for a regional bank with AUC of 0.86 using XGBoost, and constructed a pipeline from data retrieval to ◦ validation in order to automate and reproduce the prediction workflow Configured model and app parameters for local and RDS environments and deployed a flask app on AWS EC2 to help the bank monitor ◦ the risk to churn among its customers to ultimately increase customer retention Nobel Laureates Analysis: https://github.com/tiannfff/Data-Visualization-Project • Created an interactive dashboard using D3.js to explore Nobel Laureates by country, age, and prize category ◦ Customer Purchase Prediction: • Generated 20+ features measuring frequency, recency, and other purchasing behaviors of customers for an online bookseller ◦ Built logistic regression, multiple linear regression, and stepwise regression models in R to identify top customers based on expected ◦ purchase amounts in response to a promotional offer and achieved a capture rate of 40% ELLIOT M. GARDNER (630) 432-0043 ∙ [email protected]

EDUCATION Northwestern University, Evanston, IL Sep 2018 – Dec 2019 (Expected) M.S. in Analytics GPA 4.0/4.0 Relevant Courses: Predictive Analytics, Data Mining, Data Visualization, Big Data, Deep Learning, Optimization Projects: Insurance Risk Engineering Evaluation, Concert Sell-Out Prediction, Building Retrofit Data Generation

US Army Intelligence Center of Excellence, Fort Huachuca, AZ Jan 2014 – Oct 2014 Skills Developed: Management of teams, Collaborative intelligence analysis, Direction of data collection activities

United States Military Academy, West Point, NY Jun 2006 – May 2010 B.S. in Mathematical Sciences with Honors GPA 3.95/4.0 Relevant Courses: Linear Algebra, Numerical Analysis, Mathematical Modeling, Graph Theory, Applied Statistics

SKILLS • Programming Languages: R, Python, Java, SQL • Software: Tableau, Palantir, MATLAB, , Windows • Business: Leadership in high stress situations, Non-technical presentations on technical topics, Teamwork • Military Certifications: Ranger, Airborne, Air Assault, Expert Infantryman Badge

WORK EXPERIENCE Data Science Intern Jun 2019 – Aug 2019 Health Care Service Corporation, Chicago, IL • Analyzed customer service surveys, linking respondents with membership and service data in order to model customer Net Promoter Score responses and identify key drivers leading to promoters and detractors • Presented findings and methodology to cross-domain data science teams as well as departmental and divisional leadership, to include possible follow-on work and improvements to modeling • Established a robust, adaptable data ingest pipeline for API-based data that previously had not been routinely accessed, which was adopted by another data science team for related projects

Company Commander May 2016 – May 2018 Headquarters Support Company, III Corps, US Army, Fort Hood, TX • Managed 550 soldiers assigned to a headquarters company, tracking their training status and readiness • Provided logistical support for over 900 personnel while deployed in Kuwait, providing weapons, ammunition, and equipment for movement into Iraq

Security Management Officer Nov 2014 – May 2016 85th Civil Affairs Brigade, US Army, Fort Hood, TX • Incorporated reporting into collective situational understanding, facilitating higher level decision making • Assisted in administration of the Information Management program and set standards for field reporting

Intelligence Analysis Officer Apr 2012 – Jan 2014 101st Airborne Division, US Army, Fort Campbell, KY • Briefed senior officers on intelligence developments within the province, supplemented by delivering “deep dive” analysis projects on local tribal dynamics, attacks trends, and potential sources of civil strife • Supervised 12 intelligence analysts, monitoring their analysis of intelligence reporting, direction of assigned aerial and ground-based intelligence collection platforms, and publication of a daily intelligence summary

Infantry Platoon Leader May 2010 – Apr 2012 101st Airborne Division, US Army, Fort Campbell, KY • Led 18 soldiers in conducting patrols and combat operations while deployed to Kunar Province, Afghanistan • Planned and facilitated individual and collective training, including a team-level live ammunition exercise

INTERESTS • Audio Engineering, Music Discovery, Running, Hiking, Camping, Maps/GIS Max Holiber (914) 552-2696 • [email protected] • linkedin.com/in/max-holiber • github.com/maxholi

EDUCATION NORTHWESTERN UNIVERSITY EVANSTON, IL Master of Science in Analytics, Sep 2018 – Dec 2019 Coursework: Supervised & Unsupervised Learning Methods, Database Design, A/B Testing, Hadoop, Production-ready Code, Data Visualization, Analytics Consulting, Text Analytics, Optimization, Deep Learning

UNIVERSITY OF MICHIGAN ANN ARBOR, MI Bachelor of Science in Mathematics of Finance & Risk Management, Minor in Spanish, Sep 2010 – May 2014

PROJECTS • MS Program Practicum: Created demand forecasting tool for ABC Supply Co.’s product portfolio (R, Tableau) • Built machine learning web app to predict Hall of Fame odds for NBA players (Python, AWS, Flask, HTML) • Performed K-means clustering on Lancaster Eagle-Gazette users to provide actionable business strategies (R) • Predicted spend and response likelihood for a bookstore’s marketing campaign (R, Linear & Logistic Regression) • Developed model to predict wine quality based on its chemical makeup (R, Tree-Based Models, Neural Networks)

TECHNICAL SKILLS Python • R • SQL • Tableau • Spark • Hive • AWS • Bash • Git • Alteryx • • MS Office • Math Tutoring

PROFESSIONAL EXPERIENCE GODADDY INC. KIRKLAND, WA | INTERNET Data Science Intern, Jun 2019 – Sep 2019 • Trained a predictive model in Python to extract the most impactful variables in determining domain activation for Senior Marketing Leadership • Created reusable in Hive with > 100 million records of orders and customer data to allow for integration and feature engineering with PySpark • Provided insights on conversion and product add-on rates based on user website behavior to influence marketing decisions and revenue tracking • Automated Tableau dashboards through Hive queries to track the performance of company SEO and website design campaigns

THE BANK OF NEW YORK MELLON NEW YORK, NY | FINANCIAL SERVICES Specialist, Quality Analytics, Aug 2016 – Apr 2018 • Conducted key driver regression analysis on textual data to determine the most impactful attributes behind client satisfaction • Built a process in Alteryx to merge and clean disparate data sources in order to launch a corporate-wide VoC program and ingested results into Tableau via API connection • Designed and developed Tableau dashboards monitoring key corporate metrics that were distributed to 10,000+ employees across the organization

WOLTERS KLUWER NEW YORK, NY | INFORMATION SERVICES & SOFTWARE Data Analyst, Governance, Risk & Compliance, Jul 2014 – Aug 2016 • Identified top candidates for sales representative assignments based on past spending and tenure • Built ETL pipeline to automate customer insights dashboards in Tableau for Executive Leadership • Implemented customer segmentation program for the company’s legal research print business Data Analyst Intern, Customer Insights, Jun 2013 – Aug 2013 • Developed prototype and metrics for a client lien portfolio benchmarking tool NAOMI ARCADIA KADUWELA

+1 (312) 438-7687 [email protected] www.linkedin.com/in/NaomiKaduwela

SUMMARY Energetic and passionate digital leader with global experience. Hands-on Data and Analytics subject matter expert. Strong business domain experience in Healthcare, Industrial, Manufacturing, and Financial Services. Graduate of GE Digital Leadership Program. Academic researcher and conference speaker in Data Science and AI

PROFESSIONAL EXPERIANCE Kavi Global, Barrington, IL Jun 2019 – Aug 2019 Consultant, Commercial Analytics • Formulated the growth strategy for the Data and Analytics Services, Software and Solutions firm consisting of New Diagnostic Business Development Process, Marketing Realignment, and Website Redesign

GE Digital Healthcare, Waukesha, WI Feb 2016 – Sep 2018 Technical Product Manager, Business Analytics Feb 2017 – Sep 2018 • Led an agile, global, matrixed team of 22 in India, Hungary and Poland to deliver $14M incremental revenue • Led R&D: Modeling projects in Sentiment Analysis, Anomaly Detection and Root Cause Analysis

Senior Analytics Engineer Feb 2016 – Feb 2017 • Managed an agile, global, matrixed team of 8 in India. Helped create a $3.6B new IoT revenue stream. Product portfolio: IoT Asset Data Rule Engine for Automated Commercial Lead Generation, Customer Propensity to Purchase Scoring for automated prioritization, and Chatbot for conversational insights • Created execution framework for Data Science initiatives, which was adopted as company standard

GE Capital, Digital Technology Leadership Program, CT, IL, WI Feb 2014 – Feb 2016 Two-year program with 4 cross business rotations. Hands-on experience delivering on top digital initiatives • BI & Analytics Lead, Healthcare: Secured $3M seed funding to launch global analytics program • Developer, Capital Bank: Enabled self-service for the marketing team to update web campaigns • Project Manager, Rail Services: shop floor, automated visibility into $65M repair budget • Simplification Leader, Capital: Enabled self-service IT support, achieving 17% improvement

GE Capital, Norwalk, CT Jun 2013 – Aug 2013 • Intern Business intelligence: Designed, developed, and automated data quality and productivity metrics

Lawrence Berkeley National Laboratory, Berkeley, CA Jun 2012 – Aug 2012 • Intern, Software Development: Created a modern framework to visualize calculations of submicroscopic behavior of electrons in matter for the scientific community leveraging research findings • Publication: Hard X-ray Photoemission: An Overview & Future Perspective. International X-Ray Conference

LEADERSHIP TRAINING GE Leadership Institute, Crotonville, NY • Designing Customer Experiences • Activating Your Leadership Journey

EDUCATION • MS in Analytics, Northwestern University, IL. December 2019 • Certificate in Business Management, Indiana University, IN. 2016 • BS in Computer Science and Psychology, Ithaca College, NY. 2013

CONFERENCES, AWARDS & RECOGNITION • Kellogg Symposium Session Facilitator: Next Steps in Your AI Journey, Northwestern University 2019 Brainstorming and flip-charting session: Business Value Co-Creation with AI • Conference Speaker: Analytics Exchange: Women in Data Science. Is Pain a Self-fulling Prophecy? 2018 • Placed 3rd in Data Science Hackathon, Northwestern University, 2019 • Winner of five GE CIO Impact Awards in Operational Excellence and Productivity. 2013-2018

PERSONAL INTERESTS • Education (Raised $110K and travelled to build 2 schools in Burkina Faso), Healthcare. Volunteering. Traveling (Traveled to 55 countries so far). Painting (Watercolor/AI). Music (Piano/Vocal). Karate. Yoga GRADUATE COURSEWORK • Data Science: Data Mining, Predictive Analytics, Deep Learning, Text Analytics, Optimization and Heuristics, Analytics for Big Data, fMRI Analysis and Methods: Topics in brain, behavior, and cognition • Data Engineering: Database and Information Retrieval, Data Management for BI, Data Visualization • Business: Leadership Skills for Data Scientists, Analytics Value Chain, Generating Business Value with Analytics

UNDERGRADUATE COURSEWORK • Computer Science: Principles of Computing Science, Database Systems, Programming Languages, Software Engineering, Operating Systems, Algorithms and Data Structures, Virtual Reality • Psychology: Statistics in Psychology, Research Methods, Social Psychology, Proseminar in Motivation, Cognition, Personality, Industrial and Organizational Psychology, Research in Psychology

TECHNICAL SKILLS • Data Science: SPSS, SAS, MATLAB, Python/Keras/NLTK/spaCy, R, Spark ML, TensorFlow • No Code | Auto ML: Plexa (Data Engineering), Advana (Data Science) | H2O (Auto ML Hyper Parameter Tuning) • Data Engineering/Visualization: Informatica, Talend, SQL, HVR, SAP Business Object, Spotfire, Tableau, D3 • Big Data/Databases: Hadoop/Hive/MapReduce, Oracle, Teradata, Greenplum, MySQL, Postgres, MongoDB • Programming Languages: Java, JavaScript, Scala, C/C++, HTML/CSS, R, Python, Scala • Cloud Platforms: AWS, MS Azure, Google Big Query, Google Colaboratory, Kubernetes and Docker • Development Methodologies | Productivity: Agile, Waterfall, DevOps | Prezi, Lucidchart, Aha, Rally, Slack • Packaged Software: IBM Maximo, Adobe Experience Manager, ServiceNow, Salesforce

GRADUATE RESEARCH MS in Analytics, Northwestern University, IL Sep 2018 – Dec 2019 Commercial Growth: Chicago Park District – Special Event Venue Pricing Optimization Algorithms • Created value-based pricing strategy to increase margins. Designing K-Means clustering algorithm to segment demand seasonality & ARIMA time series models to forecast demand

Commercial Growth: IndyStar & Zanesville Newspapers – Personalized News Recommendation • Segmented users into behavioral user groups which could be targeted with new products based on their characteristics via personalized email news emails and updates, leveraging a K-Means clustering algorithm eCommerce: Optimizing Promotions with Strategic Customer Segmentation • Designed and implemented a combined logistic regression and multiple linear regression model to predict customer purchase value for direct mail promotional period for an online bookstore Healthcare: Deep Learning MRI Brain Tumor Classification • Classified MRI images to detect brain tumors using Xception Convolutional Neural Networks

Healthcare: AI Doctor Suite • Developed a Flask App that takes symptoms and Extra Trees Classifier classified patient risk of heart disease. Integrated Eliza Therapy Bot to chat with users, which has proven to be calming

Healthcare: Children’s Hospital of Chicago - Spinal Cord Injury Pain • Recommendations to improve patient care and recovery leveraging a stepwise linear regression model and hierarchical clustering algorithm to identify leading indicators of patients with increasing pain • Presented findings at Analytics Exchange: Women in Data Science

Art: Deep Learning AI Artist • Created art leveraging Convolutional Neural Networks (CNN) to apply Neural Style Transfer: taking a content image and style image & output an image with the combined content and style

UNDERGRADUATE RESEARCH BS in Computer Science and Psychology, Ithaca College, NY Sep 2009 – May 2013 Environment: Analysis of the Freezing and Thawing Cycles of the Arctic • Measure global warming impacts with a region detection algorithm to analyze satellite images

Environment: Fish Harvesting Simulation to Prevent Species Extinction • Determined optimal fish harvesting rates based on forecasted reproductive rates to prevent extinction

Energy: Investigating the Structure of the Western United States Power Grid: • Identified weaknesses in western portion of the U.S. Electrical Grid using network blackout simulations

Publication: Referenced by professor: Sustainability Themed Problem Solving in Data Structures & Algorithms Matthew Alexander Kehoe [email protected] | https://www.linkedin.com/in/matthew-kehoe-ab8820b5/

Education Master of Science in Analytics | Completion: December 2019 | Northwestern University · Cumulative GPA: 3.925/4.0 · Relevant courses: Predictive Analytics I&II, Intro to Databases (SQL), Data Visualization, Data Mining, Analytical Project leadership · Class projects practicing machine learning, data cleaning, presentation of analysis Bachelor of Science in Economics | May 2018 | Rochester Institute of Technology (RIT) · Minors: Mathematics, Political Science · Cumulative GPA: 3.79/4.0, Magna Cum Laude, Deans List every semester · Relevant courses: Probability and Stats I&II, CS 101 Principles of Computing, Econometrics I&II (using R), Design and Analysis of Clinical Trials, Statistical Software (R and SAS), Linear Algebra I&II · Department Nominee to speak at College Commencement · Captain of Varsity Men’s Rowing team (2017-18), All-Liberty League Rowing Team (2014-2015), National Invitational Rowing Championship and NY State Championship All-Academic Teams · Rochester Institute of Technology Founders Scholarship · Global Leadership Certificate from RIT Leadership Institute and Community Service Center

Experience Analytics Consultant | Northwestern University | Chicago, Il | September 2018-June 2019 · Solve industry problem for leading credit tracking firm. Feature engineering, machine learning modeling, and presentations. Summer Research Fellow | American Institute for Economic Research | Great Barrington, MA | Summer 2017 · Research and prepare publications to educate the public on the process of scaling Bitcoin to a larger user base and regulating Initial Coin Offerings. Presented publications at conclusion of summer fellowship. Research Assistant | RIT | Rochester, NY | Fall 2015-May 2018 · Published Behavioral Economics Research in New York Economic Review. Conducted literature reviews, carried out experiments, cleaned data and ran analysis. Communicated results at conference. Teaching Assistant | RIT | Rochester, NY | Fall 2016 · Tutor students in Intro to Microeconomics Manuscript Assistant| Cornell University | Ithaca, NY | Summer 2015 · Organize archival material, maintain online database of archives VIVO Assistant| Cornell University | Ithaca, NY | Winter 2015 · Evaluate search results to assure that Cornell faculty web profiles display research areas accurately

Skills Languages: English (Native), Hungarian (~B2), German (~A2/B1) Data analysis/Programming: R, Python, Java, SQL, D3, SAS, SPSS, CSS, HTML, JavaScript, Microsoft Office Joe Kupresanin [email protected] github.com/kupresanin99

Education

Northwestern University Graduation: December 2019 Master of Science in Analytics, Candidate in the Class of 2019

The Ohio State University Graduated June 2007 Master of Applied Statistics, Certificate in College Teaching

The Ohio State University Graduated June 2000 Bachelor of Science, Business Administration, Honors Cohort, Marketing Major

Technical Skills

Python, R, SQL, git, Linux, AWS, HDFS, Spark

Projects

Graduate Student Consultant: Collaborated with teammates to bring analytics solutions to clients. Used Python, R, SQL to retrieve, clean, model, and present data. Team projects included linear & logistic regression, boosted gradient trees, random forests, neural networks, graph networks, cluster analysis, recommendation systems, customer relation management, and ROI analyses. Collaborated using Slack, Docs, Slides, and GitHub. Topics: Household identification, hotel review sentiment analysis, online bookstore revenue prediction, newspaper readership decline study. September 2018 – Present.

Baseball Runs Prediction Web App: Used AWS to implement an S3 – EC2 – RDS Python application to serve up daily predictions after ingesting data from an API pull. Modeled with random forests selected using cross-validation. Deployed a Flask app to present results to customers. April 2019 – June 2019.

Uncle Web Knows Best Game: Invented pop culture trivia card game, ran Kickstarter campaign, managed social media, produced and distributed 400 promotional copies of game nationwide. Spring / Summer 2016.

Introduction to Statistics Textbook: Author, see Cecil College below. Fall 2013 to Summer 2014.

Work Experience

84.51 June 2019 – August 2019 Data Science Summer Intern on Stores, Assortments, and Space Mission Developed analytics plan to explain customer migration during 2018 Kroger remodeling efforts. Presented data- driven insights to consultants and management with goal of minimizing disruption to KPI during construction period. Queried data, reported on past outcomes, and modeled customer behavior for future store remodels.

Cecil College August 2007 – June 2018 Professor of Mathematics Taught 30 credits per year of statistics and linear algebra. Served as Academic Senate Vice President. Wrote introductory statistics textbook, recorded accompanying videos, designed learning management system, created online homework system. Course materials still used by ~500 students per year. Coordinated all aspects of statistics instruction for ~25 sections each year. Mentored other faculty members on flipping courses and teaching statistics.

Altria Group, Inc. June 2000 – August 2002 Territory Sales Manager, PM USA Managed 130 retail accounts (corporate & independent), sold promotions & retail space contracts, performed marketing blitz each cycle, developed customer relationships to build brand exposure, oversaw temporary staff.

Professional Involvement and Accomplishments

Evanston Scholars Mentor (2019) Northwestern University MSiA Scholarship (2018) Cecil College Faculty Sabbatical (2013) The Ohio State University Graduate Teaching Award (2007)

Sarah Michel LeRoy (573) 821-3502 | [email protected] | https://www.linkedin.com/in/sarah-michel-leroy/

EDUCATION Northwestern University, Evanston, IL Expected December 2019 Master of Science in Analytics • Honors: Internal merit scholarship from Northwestern University Rhodes College, Memphis, TN May 2019 Bachelor of Arts in Economics, minor in Mathematics • Morse Scholar: Rhodes College four-year, merit-based scholarship that covered full tuition • Honors: Graduated magna cum laude, Phi Beta Kappa, Omicron Delta Epsilon • Senior Seminar Research Paper: Analyzed Rhodes College data using a cross time probit regression to predict the likelihood of a student receiving an alcohol violation

SKILLS Software and Programming Languages: R, Python, Java, SQL, Hive, Presto, Spark, D3, Tableau, Git, AWS Modeling: Parametric and non-parametric regression and classification, clustering, time series, A/B testing, and recommendation systems

PROFESSIONAL EXPERIENCE Zillow Group Data Science Intern, Seattle, WA Summer 2019 • Using Hive, identified several key problems in a new pay per lease advertising product, leading to a 50% predicted increase in revenue for the product when resolved • Using Hive and Tableau, created an automated dashboard to alert both product management stakeholders and the software development team to these bugs in the product in real time as well as create insights into the overall product health

Welch Consulting Consultant, Washington, D.C. August 2017 – August 2018 Associate Economist August 2015 – August 2017 • Analyzed claims of gender and race discrimination in pay, terminations, hiring, and promotions using multiple regression and logistic regression analysis for class action lawsuits and consulting cases • Used Stata to clean, manipulate, and maintain large human resources datasets (4 million + records) • Prepared detailed reports of model results for Ph.D. economists, as well as clients, and prepared data visualizations for use in trial exhibits, effectively managing two to three cases simultaneously • Used Python to access the monthly Current Population Survey data from the Bureau of Labor Statistics, through the Public Data API, and manipulate the data for use in the Welch Consulting Employment Index

Federal Deposit Insurance Corporation (FDIC) Financial Institution Specialist, Columbia, SC Field Office July 2014 – July 2015 Financial Management Scholar, Memphis, TN Field Office Summer 2013 • Worked with a rotating team of 10 members to evaluate the components of an on-site bank examination: Capital, Earnings, Liquidity, and Sensitivity to Market Risk, and presented report comments and analysis to senior bank management and the board of directors • Received two “STAR” awards for outstanding performance

PROJECTS Practicum Project: Partnered with the Crime Lab of Chicago to analyze both victim and arrest datasets to predict the likelihood of recidivism, specifically related to gun violence, using supervised classification models in R

Book Recommendation System: Created a book recommendation system using a KNN model on ratings of 10,000 popular books, hosted on AWS (S3, RDS, EC2) with a web interface through the Python Flask app

Venmo Text Analysis: Used PySpark to perform a cluster analysis on 7 million Venmo transactions

Jonathan S. Lewyckyj 703-677-2875 | [email protected] Education Northwestern University, Evanston, IL Expected December 2019 Master of Science in Analytics  Coursework: Predictive Analytics I and II, Databases and Information Retrieval, Data Mining, Data Visualization, Business Communication & Analytics Consulting, Deep Learning, Analytics for Big Data (Hadoop and Spark), Analytics Value Chain, Data Warehousing, Text Analytics, Social Network Analysis  Project Work: Industry Practicum Project with BP (over a 9-month period), Upcoming Capstone Design Project

Dartmouth College, Hanover, NH June 2014 Bachelor of Arts – Economics GPA: 3.62 / 4.00  Highlighted Coursework: Econometrics, Microeconomics, Multivariate Calculus

Skills  Programming/Software: R, SQL, Python, Java, Spark (PySpark), Hadoop, JavaScript w/ D3, Tableau, SPSS, Stata, Microsoft Excel and PowerPoint  Machine Learning Techniques: Linear regression, Logistic regression, Mixed Modelling, Tree-based methods (GBM and Random Forest), Nearest Neighbors and Weighted Kernel smoothing, Cluster Analysis, Principal Components and Factor Analysis, Image Classification using Neural Networks

Work Experience Chicago White Sox Baseball Analytics Intern, Chicago, IL June 2019 – September 2019  Developed statistical models for evaluating, projecting, and developing MLB and minor league players  Performed analysis in support of potential in-season and offseason roster moves

CEB / Gartner Senior Quantitative Analyst, Financial Services Practice, Arlington, VA March 2017 – July 2018 Quantitative Analyst, Financial Services Practice, Arlington, VA December 2014 – March 2017  Employed statistical techniques such as linear, logistic, and polynomial regression, k-means clustering, and factor analysis to model customer typologies and impacts on customer loyalty and wallet share  Collected, cleaned, and analyzed datasets from customer panel surveys of up to 5,000 responses, client benchmarking diagnostics and benchmarks, and other sources  Contributed to the design of quantitative research studies, including forming and testing hypotheses  Collaborated with internal business partners and subject matter experts to identify key client problems and suggest actionable solutions to financial services executives  Led a project using R to collect and analyze Twitter data of >100,000 interactions between customers and retail banks’ customer service accounts. Performed keyword and sentiment analysis to determine customers’ pain points and identify what types of interactions and customer experiences led to positive or negative opinions about their banks

Activities Economics Study Group Leader Fall 2011-Spring 2012 Dartmouth College Rockefeller Center Management and Leadership Development Program Spring 2012 Sigma Alpha Epsilon Fraternity, House Manager Summer 2012 - Winter 2014 Dartmouth Club Baseball Team, a Founding Member Spring 2011 - Fall 2013 Personal Interests: MLB/NFL/NBA and sports analytics, bodybuilding, hiking, fantasy and science fiction Hyung C. Park [email protected] ∙ 650-417-4497

EDUCATION NORTHWESTERN UNIVERSITY Evanston, IL Master of Science in Analytics September 2018-December 2019 Cumulative GPA: 3.9/4.0 Bachelor of Science in Applied Mathematics September 2015-June 2018

Recognitions: BCG Gamma Tec{h}ack (1st Place), Nike Analytics Hackathon (2nd Place), Master of Science in Analytics Merit-based Scholarship, Applied Data Science Fellowship, Tau Beta Pi (Engineering Honor Society)

WORK EXPERIENCE NIKE Beaverton, OR Data Science Intern June 2019-September 2019 • Improved the current system for generating estimated time of arrival for inbound shipments by 50% using stacked ensemble model consisting of LightGBM, K-NN, and Neural Networks with internal supply chain data and external data from APIs resulting in cost savings of $20MM/year • Interacted with stakeholders and data engineers to productionalize and implement the model within AWS for live predictions

PNC FINANCIAL SERVICES New York City, NY Investment Banking Summer Analyst May 2017-August 2017 • Examined collaterals worth over $10B by modeling stress cases using Excel, Numpy, Pandas, Seaborn, Scikit, and VBA to structure diverse types of assets into secured products with low probability of default • Communicated risk analysis directly with other banks and clients to identify suitable borrowing base and triggers • Presented comprehensive reports on applying blockchain technology to securitization and examined how smart contracts can be applied to the fixed income market by fully developing blockchains using Ether and Hyperledger

NSF CLEMSON UNIVERSITY-DATA INTENSIVE RESEARCH Clemson, SC NSF Summer Researcher June 2016-August 2016 • Developed and analyzed benchmark performance tests of different Amazon Web Services (AWS) EC-2 cloud computing configurations and compared them to local high performance computing clusters at Clemson • Engineered cost analysis model for different AWS configurations based on consumer needs and performance levels

NATIONAL AERONAUTICS AND SPACE ADMINISTRATION (NASA) Evanston, IL Data Science Intern March 2016-June 2016 • Conducted psychological simulations on NetLogo to observe how different personal and relationship variables affect performance in an isolated environment using sentiment analysis • Extracted text data from previous NASA space missions using Python to identify behavioral variables for the simulation model

PROJECTS Honda Research and Development Analytics Consultant (NLTK, Pandas, Gensim) • Leveraged natural language processing techniques to map employees to skill sets posted in job postings and grouped similar jobs based on skillset through clustering and latent dirichlet allocation topic modeling • Designed a Digital Capacity Dimension to measure the capabilities of engineers and staff them onto the right projects

Venmo Transactions Analysis (PySpark) • Performed social network analysis to understand the distributions of Venmo’s transactions social network • Engineered text-based attributes and emojis using regex and clustered transactions to classify each type of transaction

Others: Cash Flow Waterfall (VBA), Image Recognition (Tensorflow), News Articles Text Analytics (Regular Expressions), Medical Patient Clustering Analysis (Scikit), Anime Recommendation System (Numpy, Pandas), Product Basket Analysis (Numpy, Pandas, Seaborn, Scikit), Image Captioning Project (Pytorch, Numpy), Clustering Local News Readers (R), Slack Message Analysis (D3, NLP)

ACTIVITES K-Sound-WNUR 89.3 FM Radio Evanston, IL DJ October 2018-Present • Directed weekly shows on Chicago’s WNUR radio to introduce underrepresented music from Korea

TECHNICAL SKILLS AND INTERESTS • Programming: Python, MATLAB, R, Java, Excel, SQL, Git, JavaScript, HTML, AWS, C++, PySpark • Interests: Hiking, Traveling, Soccer, Reading Kejin(Karen) Qian (872) 806-9221 | [email protected] | https://github.com/kejin-qian EDUCATION Northwestern University | Evanston, IL Expected Graduation Dec 2019 Master of Science in Analytics GPA: 4.00/4.00 • Coursework: Predictive Analytics, Data Mining, Deep Learning, Analytics Consulting, Analytics for Big Data, Data Visualization, Text Analytics, Databases & Information Retrieval, A/B Testing, Amazon AWS University of Toronto | Toronto, Canada Sept 2014 - Jun 2018 Honours Bachelor of Science with High Distinction GPA: 3.95/4.00 • Double Major in Mathematics and Statistics, Minor in Economics

PROFESSIONAL EXPERIENCE TransUnion Chicago, IL Data Science & Analytics Intern Jun 2019 - Present • Developed an automatic feature engineering algorithm using Featuretools in Python and stacked denoising autoencoders • Designed and implemented an unsupervised feature selection model: - conduct clustering on candidate features to identify feature groups - select the representative feature from each group by building an XGBoost model using all features to predict cluster numbers and select the one with the highest permutation feature importance - the feature engineering and selection model was applied to a Trade History data of 11M records, a logistic classification model was built to identify bad accounts, elevated the K-S by 5.6%, ROC by 7.4% • Designed a feature quality test by performing a k-fold CV with autoencoders, feature relationships’ stability and reliability will be tested based on the standard deviation of percentage differences between reconstruction errors on test and validation sets United Parcel Service (UPS) Evanston, IL Graduate Analytics Consultant Oct 2018 - Jun 2019 • Built an XGBoost model with ROC of 0.978 for predicting whether a package will be successfully delivered or meeting a service time commitment supplemented by external weather, road closures and census data • Implemented k-means clustering on routes and combined the results with the predictive model to investigate the relationship between clusters and last-mile successful delivery rates • Designed anomaly detection models using time series forecasting on delivery data to identify abnormal delivery days Faculty of Law, University of Toronto Toronto, Canada Machine Learning Research Assistant Oct 2017 - Apr 2018 • Performed correlation analysis to identify the feature importance on bail condition compliance and implemented recursive feature elimination via caret in R to reduce feature dimension • Built interpretable classification models (Logistic Regression, Random Forest, XGBoost, Naive Bayes) with 800k defendants’ demographic and criminal data, achieved a prediction accuracy of 82.96% and ROC of 0.87 Dept. of Mechanical and Industrial Engineering, University of Toronto Toronto, Canada Undergraduate Research Lead May 2017 - Sept 2017 • Analyzed condo segmentation based on k-means clustering; Studied the cluster centroids for feature selection • Built a regularized regression model with adaptive lasso (R! 2: 0.873) and stacked hierarchical autoencoder to predict condo price FEATURED TECHNICAL PROJECTS Venmo Transaction | Social Network and Text Analysis • Performed clustering on 7M Venmo transaction data to identify major transaction types using PySpark, SparkML and MLlib • Identified transactional relationships between users, performed user segmentation based on transaction activity data Key to Happiness | D3 Visualization Website (https://kejin-qian.github.io/) • Understood different dimensions that influence one’s subjective happiness and how those might vary across countries by doing feature selection using random forest on data collected from World Happiness Report • Designed an interactive website using D3.js, HTML, CSS to visualize findings at time, region and socioeconomic levels Toronto Datathon | Spatial Visualization & Advanced Regression • Built generalized linear models in R to investigate statistical relationships between vehicle accidents and circumstantial factors such as weather, fuel station and idle time using 293k rows of vehicle activity data • Created heatmap over city maps to visualize vehicle accident distributions using geohash in R (ggmap, ggplot2) Water Scarcity Evaluation | Econometrics Modeling • Developed water demand & supply model in R using simultaneous equations model and regression techniques • Built minimum spanning trees by Kruskal's algorithm in MATLAB to find efficient paths of water supply Malicious URL Detector | Flask Web App Design • Built an XGBoost classifier (accuracy: 91%, ROC: 0.974) to detect malicious URLs primarily using URL strings as features • Developed a full stack Flask app that hosted the model on AWS EC2, stored all user input and prediction results in RDS Menu Generator | Deep Generative Modeling • Generated new menus based on cuisine tags with CNN, LSTM and Bilateral LSTM using menu data scripted by scrapy.Spider

TECHNICAL SKILLS Python • R • Java • SQL • Hadoop • Spark • Hive • Tableau • D3.js • AWS • Git • HTML5 • CSS • MATLAB • Stata QIAO YU (FINN) 781.605.8497 • [email protected] • towardsdatascience.com/@finnqiao • github.com/finnqiao

EDUCATION NORTHWESTERN UNIVERSITY MCCORMICK SCHOOL OF ENGINEERING Evanston, IL Master of Science in Analytics Expected Graduation 2019 • Coursework: Product Management, Databases & Information Retrieval, Predictive Analytics, Java & Python, Analytics Value Chain, Analytics Consulting, Data Mining, Analytics for Big Data, Deep Learning, Text Analytics, Optimization • Networking and Industry Collaboration Leadership: Contacted and developed relationships with target companies.

TUFTS UNIVERSITY Boston, MA Bachelor of Arts, summa cum laude, Economics September 2014 – February 2018

PROFESSIONAL EXPERIENCE tryb Group Singapore Product Management Intern June 2018 – August 2018 • Worked closely with management in developing a loan analytics platform for structured finance products in ASEAN. • Mapped out user journeys and product features based on interviews with target financial institutions and investors. • Proposed relational database design with accompanying data flows, design schemas, and data dictionary.

GuarantCo London, UK Internal Product Intern - Finance June 2017 – August 2017 • Drove the development of a pipeline reporting process to effectively visualize and analyze key deal information and trends.

Tufts Entrepreneurs Society Boston, MA Co-Director, Strategy and Development January 2016 – May 2017 • Co-founded a late-night food service and a food waste repurposing startup on campus, utilizing lean canvas for fast ideation.

FEATURED TECHNICAL PROJECTS & PUBLICATIONS Towards Data Science (more articles at https://towardsdatascience.com/@finnqiao) Data Science Writer • Utilized Datashader and Dask for efficient visualization of large datasets of geolocation data on San Francisco businesses. • Built optimization models with SciPy and PuLP to analyze pricing schemes and inventories for LA Metro Bike share. • Applied NLP preprocessing framework on Apple App Store descriptions and identified app clusters with K-means cluster. • Created cohort analysis with pandas for sales and retention rates of e-commerce customers to analyze purchase patterns.

Munchmates Group Lead, Python Developer • Led team of three engineers in creating a react native app connecting young professionals with pop-ups and food trucks. • Managed relationships with users, vendors, and content partners, and conducted interviews to aid agile product planning. • Scraped vendor and geojson data from over 300 vendor and partner sites with beautifulsoup, selenium, and requests. • Developed a scoring algorithm that accounted for demographic biases and personalization with numpy, nltk, and TextBlob.

Network Analysis of Ingredients in Recipes (https://sites.northwestern.edu/msia/2019/05/21/chocolate-chips-and-fish-sauce-a- network-analysis-and-visualization-in-ingredient-pairings/) • Conducted network analysis on ingredients in recipes and used a custom metric favoring rare ingredients for edge weights. • Designed a force-directed D3 graph that allowed users to filter network edges by strengths of different edge weights.

Airbnb D3 Visualization Website (https://finnqiao.github.io/spain_airbnb/) • Isolated pricing and availability trends in Pandas for Airbnb in Spain around specific events and landmarks. • Designed an interactive scrolling storyboard using D3.js and Illustrator focused on geographical and temporal data.

Other Featured Projects • Performed social network analysis and text analysis on 7M Venmo transactions using PySpark and SparkML. • Generated new menus based on cuisine tags with CNN and LSTM models with online menu data scraped with Scrapy spider. • Developed pricing plan for Chicago Parks with seasonal and venue premiums based on ARIMA and clustering models. • Built full stack Flask web app that hosted a model predicting average funding amounts based on startup characteristics. • Identified unique reader interest groups for SF Chronicle from clustering on TFIDF features generated from article content.

ADDITIONAL EXPERIENCE • Trained under renowned chef Eric Sampietro as his apprentice in his Michelin star restaurant in Gers, France. • Established the operational, investment, and risk control framework for a 50M private placement at JIMUBox Shanghai. • Supervised and conducted training for over 300 recruits as a Platoon Sergeant in the Singapore Armed Forces.

SKILLS Python • R • Java • SQL • Javascript • D3 • HTML5 • CSS3 • Swift • Tableau • Node.js • MongoDB • Heroku • Git • Docker

Shiva Ram Venkat Ramanan MS IN ANALYTICS CANDIDATE

PROFESSIONAL EXPERIENCE

GoDaddy, Cambridge, MA June 2019 – Sep 2019 Data Science Intern Enabled better early identification of shifts in the business by improving the accuracy of time series forecasting models to foresee future revenue through renewals for each month. The model was built at a highly granular level using bottoms-up approach so that the forecast can be rolled up to any desired level (country, region, product etc.). Migrated the forecasted monthly renewal revenue to daily renewal revenue by allocating the monthly forecasts to each

day of the month based on day level seasonality. (224) 428-5729 [email protected] Chicago Park District, Chicago, IL Sep 2018 – June 2019 MSiA Practicum Engagement – Data Science Consultant linkedin.com/in/shiva1394/ Developed a robust pricing framework for the 500+ Special Event Venues by creating an analytics based venue price by accounting for seasonal/venue based demand fluctuations

EDUCATION Mu Sigma Business Solutions, Bangalore, India June 2015 – June 2018 Decision Scientist

Master of Science in Analytics Exp Dec 2019  Enabled savings of $2M per year for the third largest Australian Health Insurer by Northwestern University, Evanston, IL designing and implementing an analytical framework which reduced the number of policy Expected Coursework: Predictive Analytics, Deep lapses occurring every month. The framework was developed based on the results of two Learning, Text Analytics, Social Network Analysis, classification models, one predicting the customers at a high risk of lapse and the other Data Visualization, Data Mining, Big Data, predicting the best time of the day to contact the customer Databases  Partnered with Supply Chain Analytics team of a US based Fortune 500 pharmaceutical company to optimize inventory stocking levels and maximize cash-flow Bachelor of Engineering Manufacturing Apr 2015 o Reduced demand forecast error at a SKU (Stock Keeping Unit) level by 40% by College of Engineering, Guindy, India building a time series demand forecasting model. The model was an ensemble of Relevant Coursework: Mathematics I & II, Probability and Statistics, Finite Element Analysis, ARIMA, XGBoost, SVM and Exponential Smoothing time series models. The model Numerical Methods, Operations Research output was visualized in an intuitive R Shiny app which enabled end business users to seamlessly use the new forecast to make strategic decisions SKILLS o Managed a team of six to segment rare disease drug SKUs using unsupervised learning techniques and found segments with high probability of stock out. Built a classification model to predict stock out situations for the SKUs in high risk segment R Python SQL Java so that a customized stock out strategy can be used for these SKUs  Teaching and coursework at Mu Sigma Business solutions: Tableau Rshiny SAS o Mentored 10 batches of newly employed trainees by providing them a mock project experience. Assisted all the way as the trainees solved and presented back their

approach and solution to various real world analytics problems. AWARDS AND CERTIFICATION o Designed SQL and Code Design Principles coursework. Taught over 650 inductees o Conducted accelerated leaning programs for around 50 employees assigned to an Spot Award Sep 2016 Australian Insurance account by conducting sessions on insurance business, design Decision Scientist Certification Feb 2016 thinking, SQL and R

FEATURED ACADEMIC PROJECTS Decision Scientist Trainee  Created data warehouse to support all business analytics and data-driven decision- . Restaurant menu generation based on cuisine making needs of one of Australia’s largest general insurance companies. The data choice using deep learning (CNN and LSTM) warehouse is now used as their single source of truth and it also reduced the batch job . Developed a Flask Web App to predict PUBG runtime by 50% finish place and hosted the app in AWS  Effectively managed $1.5M revenue stream with the Australian Insurance company. Led . Game analytics: Player Profiling and Retention a team of ten, working in agile methodology, designed and built sales, portfolio and lapse Prediction using tensor factorization in Just dashboards in Tableau after establishing the reporting requirements and reporting KPIs Cause 2 with the business RACHEL ROSENBERG (214) 909-9680 ▪ [email protected] ▪ rosenbergrachel.weebly.com

EDUCATION Northwestern University | Evanston, IL Expected Graduation December 2019 Master of Science in Analytics • Student Leadership Board | Responsibility for new student outreach and marketing. Texas A&M University | College Station, TX December 2017 Bachelor of Science in Chemical Engineering, cum laude, Minor in Anthropology, Honors Fellow

PROFESSIONAL EXPERIENCE Civis Analytics Applied Data Science Intern | Chicago, IL June 2019 – Present • Built ETL pipeline for timeseries modeling using a combination of SQL and Pandas. • Served models predicting user behavior for several products in a dashboard using R Shiny and Civis’ internal Platform software, utilizing Docker images and parallel model-running tools. • Prepared digital streaming data for use as a proxy in first-party media attribution project. • Composed pitch for new client with emphasis on big-picture insights and storytelling for sales. Intel Corporation January 2018 – July 2018 Liquid Industrial Waste Systems Intern | Hillsboro, OR & May 2017 – August 2017 • Modeled expected vs actual lift station usage in JMP to aid in decision to expand systems in factory. • Led deployment of gas and chemical inventory management system. Designed system with multiple safety and security checks to ensure ease of use by technicians and performed onsite use test experiments. Bulk Chemical Distribution Intern | Chandler, AZ June 2016 – August 2016 • Performed lab experiments to qualify ion chromatography system for chemical blending. • Led waste disposal project for bulk system qualification. Project saves $2.8 mil/year.

FEATURED TECHNICAL PROJECTS & PUBLICATIONS Markov Chain Model for Sequencing Yoga Classes https://sites.northwestern.edu/msia/2019/06/26/happy-baby-to-goddess-creativity-in-yoga-sequencing-with-markov-chains/ • Created Markov Chain model in Python Pandas to build innovative sequences for yoga classes. • Creatively visualized generated sequences using Matplotlib, Pillow, and Canva. • Built in checks to ensure that classes were accessible while maintaining variety and novelty. Applied Data Science Research Fellow for Fortune 100 Automobile Company • Calculated a “capacity” metric for each engineer across divisions, representing ability to contribute more or less work per unit time, to assist decision making for headcount reallocation. • Designed Conjoint Analysis experiment to gauge managers’ priorities when hiring and assigning work. Other Featured Projects • Produced full-stack Flask app using Agile methodology to predict success of mountain climbs; based in AWS EC2 and Ubuntu, with data management through S3 and RDS. • Conducted sentiment analysis of hotel reviews using an LSTM in Tensorflow and logistic classification. • Built interactive D3 visualization to display differences in AirBNB data between two cities. • Performed text analysis of >7M Venmo transactions using Pyspark and SparkML. • Used KNN clustering on TF-IDF features to segment digital subscribers of a major newspaper.

SKILLS Python • R • AWS • SQL • Javascript • D3 • Spark • Hadoop • Git • Tableau • JSL • RYT-200 Yoga Instructor

Shreyas Sabnis [email protected]| 773-739-4562| linkedin.com/in/shreyassabnis| github.com/sabnisshreyas91

Education

Northwestern University Master of Science in Analytics | GPA: 3.9/4.0 December 2019 (Expected) Coursework: Predictive Analytics, Data Mining, Big Data Analytics, Deep Learning, Analytics Value Chain & A/B testing

M.S Ramaiah Institute of Technology Bachelor of Engineering, Mechanical Engineering | GPA: 9.11/10 May 2013

Skills  Programming & Databases Python (pandas, matplotlib, scikit-learn, StatsModels, BeautifulSoup, pyspark, Keras, TensorFlow, seaborn, SQLAlchemy, xgboost), R (ggplot2, dplyr, data.table, caret, sparklyr), Java, d3.js, MS-SQL, MySQL, PostgreSQL, SQLite, Apache Hive  Software & Framework AWS Suite (S3, EC2, RDS, CLI), Apache Hadoop, Azure ML, Flask, SQL Server Analysis Services (SSAS), Tableau, Git

Select Academic Data Science Projects

 Airbnb next booking prediction (http://18.221.171.51:5000/) Employed the AWS suite to deploy a flask app powered by an XGboost model to predict a user’s future travel destinations  ProScanner - Written text recognition Built deep learning model composed of 2 CNN blocks, 1 bi-directional LSTM & a language model with an accuracy of 89.5%  Warming up to new energy - Interactive d3 visualizations (https://lets-get-visual.herokuapp.com/story)

Professional Experience

TransUnion LLC (Chicago, U.S) - Data Science Intern June 2019 – Present

 Worked with the Digital Marketing team to improve the lookalike (LAL) audience generation process by: - Profiling individuals in the input data (principal component dimensionality reduction + K-means clustering) to identify distinct types of individuals. This improved subsequent response models’ AUC by 5% & reduced overlap between LAL audiences by 15% - Using XGBoost response models with Bayesian hyperparameter optimization to increase tuning speed. Improved AUC by 4% over existing models  Built a syndicated audience generator using pyspark & hive. Processed nearly 700 million rows of data and performed data manipulation & noise addition using spark DataFrame API and spark SQL. Tool generated audiences in ~35 minutes

Blue Cross Blue Shield of IL (Chicago, U.S) - Analytics Consultant October 2018 – June 2019

 Built a recommender engine to recommend the most cost-efficient physicians to patients based on medical history & past physician interactions. The system was packaged as a flask API for deployment to the client’s online search directory

Central Drug Research Institute (Bangalore, India) - Research Intern September 2017 – March 2018

 Compiled a database consisting of over 3000 data points of HIV/AIDS epidemiology metrics for North America by web scraping 300+ publications. Data was used by researchers to predict high-risk demographic groups for 2015-2025

Thorogood Associates (Bangalore, India) - Business Intelligence & Analytics Consultant |Technical Lead July 2013 – 2017

 Delivered a PoC in Azure ML studio to predict bodily liability insurance claims. Employed logistic regression with SMOTE to handle class-imbalance. Obtained F1 score of 65%. PoC was featured in subsequent marketing events  Developed SQL stored procedures to intelligently assist in sales rep – store territory mapping by guiding corrections to the input mappings. Reduced turnaround time from 2 days to 30 minutes with no errors  Interacted with stakeholders to gather requirements, plan user acceptance tests and production deployments in 6+ projects Surabhi Seth (224) 714-8401 | [email protected] | linkedin.com/in/surabhi-seth/

Education

Northwestern University (Evanston, IL) Dec 2019 (Expected) Master of Science in Analytics Relevant Coursework: Predictive Analytics, Data Mining, Data Visualization, Analytics for Big Data, Deep Learning, Analytics Value Chain, Text Analytics, Optimization & Heuristics

UP Technical University (Lucknow, India) Jun 2004 Bachelor of Technology (Computer Science & Engineering) Relevant Coursework: Data Structures, Database Management Systems, Design Analysis of Algorithms, Object Oriented Programming, Information Systems

Skills

Python, R, Java, C/C++, SQL, PySpark, Tableau, Git, Eclipse, IBM Cognos, Hive, Hue, Impala

Technical Projects

ABC Supply Co. Graduate Student Consultant | Nov 2018 – May 2019 o Forecasted future demand by analyzing buying patterns across thousands of SKUs using time series analysis and demand classification methods. Enova Data Smackdown Top 5 Finalist | Jan 2019 o Predicted real estate investments that produce the best returns on investment, exercising linear, logistic and stepwise regression with tuning done using k-fold cross validation. Other Academic Projects o Performed sentiment analysis using NLP techniques and deep learning LSTM models on hotel reviews. o Identified subscriber segments for SF Chronicle by applying clustering on user activity and reading history.

Professional Experience

GoDaddy (US) Summer Intern | June 2019 – Aug 2019 o Created machine learning models to predict which customers were most likely to choose a competitor for their next venture. o For marketing suitable product offerings and measuring the impact of such marketing campaigns, identified unique segments (using clustering) from customers at risk of migrating to a competitor. o To help gauge the worldwide regions growing the most in internet ventures, created deep learning models to predict the region of operation from the website URLs. ThoughtWorks Technologies (India) Lead Business Analyst | Mar 2015 – Aug 2018 Sales Model Allocation (Caterpillar, US) o Explored ERP data from multiple data sources (using SQL and R) to conduct data cleansing and feature engineering. o Developed a mechanism to classify parts sales to a product family with 90% accuracy, which provided key metrics needed for C-level reporting. Opportunity Lead Generation Analyzer (Caterpillar, US) o Identified the causes of leakages in the aftermarket parts sales by analyzing dealer data. o Designed a Hadoop based BI product providing preventive maintenance leads. The product was instrumental in plugging the leakages in sales funnel, leading it to be adopted by 100+ dealers. o Defined the product roadmap, managed the client’s feedback and helped the client’s team adopt agile practices enabling monthly product releases. AdFloe Sales Platform (Exterion Media Group, UK) o Created user journeys for inventory booking, approval and customer agreement process for campaign management, reducing the customer service response time from a week to couple of days. Tata Consultancy Services (India & US) Assistant Consultant | Sep 2004 – Mar 2015 Money Movement (Morgan Stanley, US) o Led the business analysis for this multi-phase program that aimed at providing a seamless money movement experience to the clients, financial advisors and the back-office operations through a single online banking platform. o Ran workshops and focus groups to understand user needs and the requirements for product customization. o Worked closely with the delivery team to ensure that the delivered product met client’s expectations. Tova Sara Simonson www.linkedin.com/in/tova-simonson • www.github.com/tsarax • [email protected]

EDUCATION Northwestern University, McCormick School of Engineering Evanston, IL Master of Science in Analytics December 2019 (Expected)

• Relevant Coursework: Supervised & Unsupervised Learning Methods, Data Visualization, Analytics Consulting, Database Design, Deep Learning, A/B Testing, Production-ready code, Hadoop, Text Analytics, Social Network Analysis

Scripps College Claremont, CA Bachelor of Arts in Economics, Honors and Cum Laude (Major GPA: 3.83) May 2018

• Thesis: Analyzing the effectiveness of home-sharing regulations through impacts on the long-term housing market

SKILLS

Programming Languages: SQL, Python, R, LookML, BQML, PySpark, HTML, CSS Software: , Tableau, Git, Spark, Hadoop, AWS (EC2, S3, RDS), GCP, Google Analytics, Salesforce, Marketo

PROFESSIONAL EXPERIENCE

Looker Data Sciences Inc. (pending acquisition by Google Cloud) Santa Cruz, CA

Marketing Automation Intern, Customer Experience (CX) Marketing Summer 2019

• Built predictive model on upsell likelihood for targeted campaigns using python and cross-functional data sources • Automated entire pipeline for campaign targeting by utilizing Looker and Marketo APIs within python scripts • Provided statistical guidance on sales pipeline forecasting model using BQML in Looker • Designed additional projects for the team such as A/B testing, personalized content marketing, and churn risk

Education Analytics Intern, Customer Success Summer 2018

• Built LookML models for customer education data from scratch within the Looker platform (SQL, LookML) • Identified quantitative and qualitative requirements to measure customer training and course effectiveness • Developed interactive dashboards and new education KPIs for all customer focused departments • Analyzed Google Analytics data to identify website traffic trends for training and other customer resource pages

AGCO Corporation Duluth, GA

Global Talent Management Intern, Human Resources Summer 2017

• Developed monthly global reports with visualizations of talent acquisition KPIs and recommendations and presented reports on monthly global conference calls • Initiated data project to determine efficient and effective courses for internal training PROJECTS

Blue Cross Blue Shield of Illinois Data Science Consultant October 2018 – June 2019 • Built recommendation system for BCBSIL on a team of five students (Ensemble method, Python, R, Flask)

House Price Predictor Engine April 2019 – June 2019 • Created web-based machine learning app to predict housing prices for a user (HTML, CSS, AWS, Python, Flask)

Newspaper Clustering January 2019 – February 2019 • Clustered readers in order to push stronger engagement and decrease churn (K-means Clustering, R)

Predicting Kickstarter Campaign Success January 2019 – March 2019 • Developed classification model based on campaign attributes (Tree-based Models, Naïve Bayes, R)

Predictive Analytics for Online Bookstore October 2018 – December 2018 • Identified campaign response likelihood and customer purchase outcomes (Linear & Logistic Regression, R)

Molly A. Srour https://www.linkedin.com/in/mollysrour • St. Paul, MN • 310-469-4645 • [email protected]

Dedicated analytics professional focused on the intersection of data science, genomics, and healthcare with experience in the manipulation of massive datasets using predictive analytics and machine learning. Engaged communicator interested in linking business development to analytic innovation.

EDUCATION

Northwestern University, McCormick School of Engineering, Evanston, IL Master of Science in Analytics (MSiA), GPA: 3.96 Anticipated December 2019

Honors: MSiA Merit Scholarship (September 2018-Present), Applied Data Science Fellowship (October 2018-June 2019) Coursework: Databases and Information Retrieval (SQL), Predictive Analytics I/II, Data Mining, Analytics Value Chain (Model Deployment/Reproducibility), Data Visualization, Deep Learning, Spark, HDFS, Data Warehousing, Text Analytics

St Olaf College, Northfield, MN Bachelor of Arts Mathematics, Music, GPA: 3.82 May 2018 Honors: Magna cum laude; Pi Mu Epsilon National Mathematics Honor Society; Pi Kappa Lambda National Music Honors Society; St. Olaf College Dean’s Scholarship (August 2014-May 2018); National Merit Scholarship (August 2014- May 2018); Winston Cassler Music Scholarship (August 2014-May 2018); St. Olaf College Dean’s List (6 semesters)

TECHNICAL SKILLS

• Programming Languages: R, Python, Java, SQL, JavaScript, D3.js, PySpark, HTML, CSS • Software: Tableau, Hadoop, Git, AWS (S3, RDS, EMR, EC2), MDX, StreamBase, Bitbucket, MATLAB, Docker

PROFESSIONAL EXPERIENCE

Data Science Intern, OneOme, Minneapolis, MN January 2019-August 2019 • Contributed to the development of a pharmacogenomic risk stratification algorithm in R and Python using non- parametric predictive models and unsupervised learning methods • Aided in the creation of a software development pipeline to create a production-ready version of said algorithm • Created visualization dashboards in Tableau for communicating commercial operations KPIs and translating scientific developments into actionable business decisions Undergraduate Research Assistant, University of Minnesota, Minneapolis, MN _ June 2017-August 2017 • Tested parameters and created code for a label propagation algorithm in MATLAB that utilized semi-supervised learning to detect remote homology across protein species using datasets ranging from 10,000 to 1,000,000 rows Undergraduate Research Assistant, Brandeis University, Waltham, MA_ May 2015-July 2015 • Designed and performed biophysics experiments on actin proteins involving Total Internal Reflection Fluorescence (TIRF) microscopy; interpreted results using ImageJ software and statistical analysis

PROJECTS AND PUBLICATIONS

• Analytics Consultant October 2018-June 2019 Created HR analytics algorithm in collaboration with Kellogg School of Management, ZealStrat, and a leading automobile manufacturer (R, Python) • Spark Text Analytics May-June 2019 Utilized PySpark to classify 7 million Venmo transactions, including emoji data (Python, Spark) • Recommendation System Web Application April-June 2019 Created and deployed a collaborative filtering recommendation system with a functional web application interface (AWS (S3, RDS, EC2), Python, HTML, CSS, Flask, Git) • Clinical Data Analytics January-March 2019 Developed a classification model to predict occurrence of bacterial infection (gram negative or gram positive) among critical care patients with a team of 5 students (R) • Olympics Visualization Website January-March 2019 Created interactive visualization website using D3.js centered around the Olympics (JavaScript, HTML, CSS) • Hybsearch Desktop Application February-May 2018 Contributed to the creation and testing of a desktop application identifying existences of intra-species nonmonophyly (JavaScript, Docker, Electron, Git) • Co-author: Petegrosso, R., Li, Z., Srour, M. A., Saad, Y., Zhang, W., & Kuang, R. (2019). Scalable remote homology detection and fold recognition in massive protein networks. Proteins: Structure, Function and Bioinformatics, 87(6), 478-491.

DHANSREE SURAJ [email protected] • (224) 428 2811 • www.linkedin.com/in/dhansree-suraj EDUCATION Northwestern University, Evanston, IL Dec 2019 (expected) Master of Science in Analytics GPA: 4.00 / 4.00 ● Expected Coursework: Deep Learning, Text Analytics, Databases & Information Retrieval, Data Mining, Predictive Analytics, Analytics for Big Data, Data Visualization, Analytical Consulting Project Leadership University of Mumbai, India Jun 2015 Bachelor of Engineering, Computer Engineering GPA: 3.75 / 4.00 SKILLS Programming Languages: Python, Java, R, SQL, VBA, HTML/CSS Frameworks: Tensorflow, spaCy, scikit-learn, NLTK, Selenium WebDriver, D3.js, Hadoop, Spark, React.js Other Skills: Git, AWS, Tableau, Relational Databases PROFESSIONAL EXPERIENCE NASA Jet Propulsion Laboratory, Pasadena, CA Jun 2019 – Sep 2019 Data Scientist Intern ● Generated topic models for NASA research proposals to determine categories of strengths and weaknesses ● Identified potential to actual major weakness topic progression to better the proposal writing process ● Implemented a pipeline to scrape over 1600 webpages using Selenium and multiprocessing libraries UChicago Urban Labs, Chicago, IL Oct 2018 – Jun 2019 Student Data Science Consultant ● Analyzed crimes related panel data and generated network features for perpetrators and victims ● Aggregated panel data to generate several individual level features and integrated centrality measures ● Implemented random forest to identify individuals at high risk of reinvolvement in crime Quantiphi, Inc., Mumbai, India Sep 2017 - Jun 2018 Business Analyst ● Led a team that leveraged US legislative data to predict passage of a bill in the Congress for The Economist ● Optimized data retrieval from on-premises Oracle database using SQL views that joined over 100 tables ● Aided the feature selection process by conducting exploratory data analysis and creating visualizations ● Achieved over 95% accuracy in prediction of bill passage in US Congress using a logistic regression model ZS Associates, Pune, India Jul 2015 - Sep 2017 Decision Analytics Associate ● Estimated the future uptake of a new product and identified key patient segments using conjoint analysis ● Implemented decision trees to aid the physician segmentation process for a product in a $30Bn market ● Designed a tool to ease projection of segmented data to an overall population of over 100K physicians ● Developed tools to automate deliverables, saving 80% of time during analysis and delivery phases of projects ACADEMIC PROJECTS Authorship Attribution Web Application Apr - Jun 2019 ● Developed a logistic regression model to classify text as ‘Michael’ or ‘Dwight’ from ‘The Office’ ● Deployed web application using AWS resources, like EC2, S3 and RDS, to server predictions for new input ● Implemented modular programming practices and ensured model reproducibility Sentiment Analysis on Hotel Reviews (Luxury European Hotels) Apr - Jun 2019 ● Generated word embeddings by training a word2vec model used as the first layer of the network ● Achieved 95% accuracy using a network with the embedding layer followed by a bi-directional LSTM layer Social Network and Text Analysis on Venmo data Apr - Jun 2019 ● Analyzed degree distributions for over 7 million transactions between Venmo users using PySpark ● Generated clusters using text-based attributes from transaction descriptions to be used for transaction classification using SparkML

TANYA TANDON [email protected] • (773) 943 1319 • https://www.linkedin.com/in/tanya-tandon/ ​ ​

EDUCATION NORTHWESTERN UNIVERSITY Evanston, IL ​ ​ MS, Analytics [3.76/4] Sep 2018 - Dec 2019 ● Coursework: Deep Learning, Text Analytics, Social Networks Analysis, Data Mining, Analytics for Big Data, Databases and ​ Information Retrieval, Predictive Analytics, Analytics Consulting, Analytics Value Chain ● Awards: BCG Hackathon, Enova Data Smackdown, Leadership Experience: Student Leadership Board ​ ​ ​

DELHI UNIVERSITY India BS, Statistics Honours [3.93/4] Jul 2014 – May 2017 ​ ​ ● Coursework: Econometrics, Design of Experiments, Operational Research, Real & Numerical Analysis, Applied Statistics ​ ● Awards: Dean's Merit List, Leadership Experience: Department Joint Secretary, Student Editorial Board ​ ​ ​

TECHNICAL SKILLS Python • R • SQL • Hive • Hadoop • Spark • Presto • Tableau • D3 • Pyspark •Java • Flask • Javascript • HTML5 • Git • AWS • Airflow • A/B testing

PROFESSIONAL EXPERIENCE PRODUCT ANALYST INTERN at Pandora Media Inc San Francisco, CA ​ Pandora is a music streaming and automated music recommendation internet radio service Jun 2019 - Aug 2019 ● Built approaches to define and understand repetition to potentially improve user retention by 10% on Pandora. ● Developed a new metric that measured repetition in radio which was deployed to a model in production in less than 3 weeks. ● Created complex data pipeline to query, pre-process and further feature extract 50 BN+ records of daily click stream data using big data tools(Hive, Spark, Presto, Airflow) to model customer churning due to repetition.

DATA SCIENCE CONSULTANT at Crime Labs Chicago, IL ​ Crime Labs partners with civic and community leaders to design programs to reduce crime and violence Oct 2018- Jun 2019 ​ ● Improved accuracy by 41% of identifying individuals at the highest risk of committing gun violence crime. ● Developed creative approach to create response variables and data pipeline for effective Machine Learning implementation. ● Evaluated 1MN+ rows of data and built Gradient Boosting, Neural network as well as Random Forest models in R .

ENTREPRENEUR IN RESIDENCE at Darwin Labs India ​ ​ Darwin Labs is a startup that makes Analytics and Blockchain based products Jun 2017 – Apr 2018 ​ ​ ● Led team of four to strategize growth of an analytics product for a blockchain based Hedge Fund. ● Saved the company $500,000 in Q2 and Q3 by profiling and segmenting highly volatile crypto-market by risk with qualitative benchmarking of $1 Million fund and effectively communicated insights and metrics to leadership in Python. ​ ​

TECHNICAL PROJECTS Kickstarter success prediction full stack app (https://github.com/TanyaTandon/Kickstarter) ​ ​ ​ ● Built a completely reproducible and modular machine learning app from proof of concept to production in Python, hosted on AWS EC2 with 70% ML model accuracy and stored customer logs in RDS Postgres database. ● Designed an interactive website integrating live pictures using CSS, HTML5 and Javascript.

Automated Caption Generation Deep Learning model (https://ibb.co/6F3JqjM) ​ ​ ​ ● Built a model that used a pre trained CNN model for an image classification task and use the last hidden layer as a LSTM decoder using transfer learning. ● Using attention mechanism and beam search, model performed 4% better n-gram BLUE score than the reference paper.

Key to Happiness D3 Visualisation website (https://tanyatandon.github.io/Key_to_Happiness/ ) ​ ​ ​ ● Combined results of World Happiness report as well as World Freedom index to see how the economy, social development, and safety related to happiness. ● Designed an interactive multi-tab website in D3.js focused on different granularity of time, space, and region

Venmo Transaction Classification ( https://github.com/TanyaTandon/venmo_social_network_analysis) ​ ​ ​ ● Used Spark RDDs and Spark data frames to cluster and classify both emoji and text transactions. ● Analysed transactional relationships between users to segment customer base to better understand customer activity.

ADDITIONAL PROJECTS ● Founder, Bridge: Negotiated with large national insurance company and Indian private schools to prototype a healthcare ​ insurance plan that led to a creation of medical team at a school benefiting 5000+ students. Awarded in 'Entrepreneur Ignition Summit' and 'Women Entrepreneurship Summit' for model and strategy. Qianqing (Katie) Tang (617)-892-1160 | [email protected] | www.linkedin.com/in/q-tang EDUCATION Northwestern University, Evanston, IL 12/2019 ● Master of Science in Analytics GPA: 3.9/4.0 ● Coursework: Predictive Analytics, Databases, Data Visualization, Data Mining, Analytics Value Chain, Analytics for Big Data, Deep Learning, Text Analytics, Optimization & Heuristics Rensselaer Polytechnic Institute, Troy, NY 05/2018 ● B.S. in Mathematics of Operation Research GPA: 4.0/4.0 ● Dean’s Honor List 2015-2018,RPI 4.0 Awards (Top 1%), Summa Cum Laude Boston College (Transferred), Chestnut Hill, MA 08/2014 - 05/2015

SKILLS ● Programming : R, Python, SQL, SPARQL, JAVA, D3, HTML, JavaScript, Hive, Spark, Hadoop ● Software: Tableau, Matlab, SPSS, LATEX, Microsoft Office, PowerBI, Git, Alteryx ● Language: Native Speaker of Mandarin; fluent in English; elementary Japanese

WORK EXPERIENCE UPS, Atlanta, GA 06/2019 - 09/2019 Analytics/Machine Learning Engineering Intern ● Explored over ~100M last mile delivery data to understand driver and route characteristics using SQL and Python ● Built Regression/Classification models to exam the driver performance and found factors that affected working hours ● Based on the model results, provided advice for On-Route Supervisors to decide which drivers to talk to and what to talk about to effectively get drivers to meet planned hours, which helped lower the cost and improve the service MProbe Inc., Palo Alto, CA 06/2017 - 08/2017 Data Analyst Intern ● Cooperated with team of Stanford Translational Medicine Program to process raw experimental data using Python ● Performed Hypothesis Tests and PCA with machine learning methods including Random Forest to analyze over 100,000 enzyme data to find specific patterns related to potential diseases using R

PROJECTS UPS Practicum Project, Northwestern University 09/2018 - 06/2019 Analytics Consultant ● Performed predictive analysis on the success of delivery for 4 distribution centers with over 70,000 packages for each and identified significant features that contributed the most to the failure in deliveries ● Studied disruptive events (e.g. Hurricane) and examined last-mile operations before, during, and after the events ● Designed interactive visualizations/simulations of the route-level analysis and disruption analysis using Python Anime Recommendation Web Application Project, Northwestern University 03/2019 - 06/2019 Individual Researcher ● Built an anime recommendation system based on the Content-Based Filtering and Collaborative Filtering results ● Wrote the web application with multiple user interface using HTML and JavaScript and built the pipeline to link local data and models to the AWS Fashion Image Processing Deep Learning Project, Northwestern University 03/2019 - 06/2019 Research Team Member ● Built a CNN Model with 11 layers of autoencoders and a KNN model training on over 5000 pictures to learn the shape of clothes and identify most similar item for the input images from the ZARA database ● Fitted a K-means model to match the colors of inputs clothes ● Created a system to find substitutes for input Blogger clothing with 73% decrease in training error using TensorFlow ACTIVITIES & MEMBERSHIPS ● Gapper International Volunteer Organization, Volunteer 07/2015 - 06/2018 ● Pi Mu Epsilon, National Honorary Mathematics Society, Member 09/2015 - 06/2018 MARCUS THUILLIER Evanston, IL | C: (415) 637-8541 | [email protected]

Education

Northwestern University 9/2018 - 12/2019 M.S. in Analytics

University of California, San Diego. 9/2014 - 6/2018 B.S. in Physics with Specialization in Computational Physics, minors in Business and Political Science

Experience

Data Science Intern 6/2019 – 9/2019 Intel Corporation | Phoenix, USA • Programed using Python to perform contract analytics inside Intel GSM to help identify key provisions with Natural Language Processing and Machine Learning regular expressions and machine learning models • Generated dashboard in R-Shiny to present results in a way that can be utilized and understood by internal client

Data Science Intern 6/2017 – 8/2017 Greentropism | Paris, France • Programed using Python to efficiently filter through hundreds of files of spectroscopic plot points, create a data base and automatize the analysis of data frames • Analyzed data frames using tools such as SVM analysis, PCA and kNN and wrote code to implement these tools in a machine learning environment • Generated charts and data visualization tools to present results in a way that can be understood by customers

Intellectual Property Litigation Intern 7/2016 Grünecker Patent Attorneys and Attorneys-At-Law | Munich, Germany • Assisted in public hearings and appeals at the European Patent Office and the German Patent Office • Assisted in research and analysis of preliminary reports from the EPO and the writing of a patent proposal

Working Student in the RF and LTE department 7/2015 – 8/2015 Intel Corporation | Munich, Germany • Optimized and extended programs using VBA on Excel templates with millions of rows to efficiently output tables and graphs in PowerPoint and command the automatic generation of names • Programed new routines in Matlab for automatic treatment of data from the RF and LTE lab • Analyzed test-results and created related Excel templates through VBA • Compilation of Excel documents to automatically generate measurement reports

Skills

Python • R • Java • SQL • Tableau • Hadoop • Spark • R-Shiny • Matlab • Visual Basic • D3 Bilingual in English • C1 Level in German • Native Speaker in French

Work and Projects

The ELOR (ELO-Rugby) – selected as MSiA’s January 2019 blog post winner Predicting Online Book Store Promotion Response – MSiA 401 Final Project Forecasting Companies’ Cost Based on Labor Market Information – MSiA 400 Final Project Practicum Project – 9/2018 – 6/2019 Capstone Project – 9/2019 – 12/2019 Arpan Venugopal [email protected] | (224) 428-5207| www.linkedin.com/in/arpan-venugopal-25312b44 EDUCATION PROGRAM INSTITUTION %/CGPA COMPLETION Master of Science in Analytics Northwestern University 3.92 (/4.0) Dec 2019 Dual Degree (Bachelor’s and Indian Institute of Technology Madras 8.05 (/10.0) Jul 2015 Master’s) - Mechanical Engineering

TECHNICAL EXPERIENCE Coursework: Predictive Analytics (Supervised learning), Data mining (Unsupervised learning), Deep Learning, Data Visualization, Big Data Analytics, Text Analytics, Analytics Value Chain Programming: Python, R, SQL, Java, JavaScript, SAS, MATLAB, Octave Framework: AWS (S3, EC2, RDS, EMR), TensorFlow, Apache Spark, Tableau, Minitab, Git PROFESSIONAL EXPERIENCE Enova International Chicago, USA Analytics Intern, Research Architecture & Platform Jun 19 – Sep 19 Member of the research team investigating new analytics methodologies and use cases to institute new and best practices within the analytics department. ▪ Extended internal model building package in R to integrate Python workflow within R. ▪ Used topic modeling and clustering on the inbound emails to customer support to identify email types. Designed a framework to auto process emails to understand the content of the email and manage customer service queues on the order of priority. ▪ Developed a flask app for text preprocessing, hyperparameter tuning, and visualization for topic models. Fincare Small Finance Bank Bangalore, India Senior Data Analyst, Banking Operations Aug 16 – Jun 18 Supported field operations team with advanced analysis and insights for loan products having a customer base of more than 2 million and managed assets of over 300 million USD. ▪ Developed a predictive model to identify probable default borrowers. Achieved a 30% reduction in the creation of delinquent portfolio worth 5 million USD during a period of high default occurrences. ▪ Implemented a credit scoring tool for loan applications based on spending and repayment pattern, borrower indebtedness, and economic attributes which recorded a 40% reduction in default behavior. ▪ Awarded ‘Employee of the Quarter’ and ‘Role-model’ performance rating for contributions towards the formulation of the annual financial plan and data-driven insights for delinquency management. EXL Services Bangalore, India Consultant, Decision Analytics Aug 15 – Aug 16 Provided comprehensive data-driven insights to a leading US retail analytics company in terms of shopper traffic, sales, and interior analytics along with management of market intelligence products. ▪ Employed ARIMA time series and regression models to forecast shopper count tracked by a former version of hardware for effective comparison with the upgraded hardware. ▪ Led the transition from a relational database to NoSQL database (MongoDB) to facilitate real-time analytics. Designed schemas and collections and replicated business as usual activities in Mongo environment. DATA SCIENCE PROJECTS Retention Prediction in Open World games Jan 19 – May 19 ▪ Built user behavioral profiles using user spatial and temporal data and applied bipartite tensor factorization for automatic representation learning and dimensional reduction to generate features to predict churn. ▪ Significant prediction improvement by the additional temporal dimension features recorded when compared to simple lifetime behavior models. (Paper under review for AIIDE and IIAI conference) Applied Data Science Fellowship Nov 18 – May 19 ▪ Part of the four students from the cohort selected to work in collaboration with Kellogg MBA candidates. ▪ Developed a framework to identify job trends and estimate department-wise resource requirements to aid in resource allocation for the human resources department of a leading automobile manufacturing company. Reproducible Machine Learning model Apr 19 – Jun 19 ▪ Built an end to end machine learning pipeline and deployed a web app on AWS to predict the market value of football players. Configured data ingestion, model building, unit tests, and logging to enable reproducibility. ANJALI VERMA +1 872 203 5359 | ​[email protected]​ | ​www.linkedin.com/in/anjaliverma2896

EDUCATION

Northwestern University, Evanston, IL Master of Science in Analytics Dec 2019 (Expected) Expected Coursework: Predictive Analytics, Data Mining, Data Visualization, Java and Python Programming, Analytics for Big Data, Databases and Information Retrieval, Text Analytics

Ramjas College, University of Delhi, India Bachelor of Science (Honors) Mathematics Jul 2014 - Jun 2017 Relevant Coursework: Linear Algebra, Probability and Statistics, Advanced Calculus, Differential Equations, Vector Analysis, Numerical Methods, Linear Programming and Optimization Ranked in top 5% of the class

SKILLS

​Programming Languages:​ P​ ython, R, SQL, C ​Software: T​ ableau, Wolfram Mathematica, wxMaxima, Microsoft Office Suite

WORK EXPERIENCE

​Tata Consultancy Services, Noida, India ​Intern​ | B​ usiness Intelligence Reporting, Life Sciences Apr 2018 - Jun 2018 ● Established a BI Reporting solution to empower clinicians on clinical study specific analytics capabilities; Created visualizations in Tableau for clinical data to facilitate safety and efficacy reviews of drug treatments for endometrial cancer in adult women. ● Identified opportunities for TCS clients to narrow down study population; Enabled them to focus on areas of concern and answer sets of medical review questions through extensive use of dashboards made for the same purpose.

KPMG Advisory Services, Gurugram, India Intern |​ ​ Research, Government Advisory Jun 2017 - Aug 2017 ● Formulated a research plan to determine the scope of mixed-land use development as an accelerator of government initiatives to establish Chennai as a Smart City. ● Analyzed ongoing government schemes in the city of Chennai and identified parameters in the sectors of infrastructure, sanitation and urban planning to evaluate the targets achieved by these schemes compared to the service level benchmarks. ● Drew insights from census data and other social data to study the extent of urban sprawl, its impact on land use patterns in India and identified the changes required in urban planning to optimize use of available resources.

PROJECT WORK

Indian Institute of Management(IIM) Lucknow, India J​ an 2016 - Feb 2016 ● Solved case studies published by Harvard Business Review: The Springfield Nor’easters: Maximizing Revenues in the Minor League To understand maximization of the management’s revenues, strategic pricing and brand positioning decisions through analysis of survey data concerning demographics and social behavior collected by the management of a minor league baseball team to determine an optimal pricing model​. ZIYING WANG 206-427-9356  [email protected]

EDUCATION Northwestern University Expected Graduation: Dec 2019 Master of Science in Analytics GPA: 3.90/4.00 University of Illinois at Urbana-Champaign Graduation: May 2018 Bachelor of Science in Statistics and Mathematics Minor in Computer Science Computational Science & Engineering Certificate GPA: 3.91/4.00 Related Coursework: Statistical Learning, Datebase, Social Network Analytics, Analytics for Big Data, Deep Learn- ing, Stochastic Processes, Data Mining, Data Structure, Graph Theory, Linear/Nonlinear Programming Technical skills: Python, R, SQL, Spark, JAVA, C++, LATEX, SAS, MATLAB, EasyLanguage (TradeStation) Platforms & Softwares: Github, AWS, Linux, JIRA, UC4, Splunk, Bloomberg, SAP Business Object, Tableau PROFESSIONAL EXPERIENCE CME Group Jul 2019 - Sept 2019 Data Scientist Intern Chicago, IL · Improving the efficiency of data analysis and decision making by constructing a Python-based pipeline for an email alert system that sends daily reports · Expending the functionality of the alert system by sending daily reports in dynamic geographical changes of the trading volume; deploying and testing this system in QA environment using JIRA and Stash · Managed the liquidity insight tool in UC4; fixed problems in the configuration of EC2 instance to bring up EMR cluster · Provided future volatility prediction to help traders make decisions by building a predictive model for hourly realized volatility using SARIMA and LSTM based on keras and statsmodel.tsa Guosen Securities Jul 2018 - Aug 2018 Software Developer Intern Hangzhou, China · Designed an internal used app to help quantitative researchers design portfolio by implementing a quantitative trans- action tool with 6 customized strategies in TradeStation · Implemented a client-facing quantitative trading app with volume-based strategies in TradeStation, which was widely used among clients and attracted new traders Hundsun Technologies Inc. Jun 2017 - Aug 2017 Quantitative Analyst Intern Hangzhou, China · Explored the components of returns for mutual funds by building multivariate regression on the weekly rates of return for 139 funds based on 7 market indexes and 28 sector indexes as dependent variables · Monitored if mutual funds follow their investment strategies based on minimized variance among weighted benchmark and mutual funds PROJECTS Web-App: Grad School Applicant Evaluation System Apr 2019 - May 2019 · Evaluated applicants’ application result based on their input background from the web using multivariate regression · Proposed minimized scores to be admitted for rejected applicants of their future exams based on the bisection method · Publicized the web-app with an EC2 instance as host; created a student database in RDS instance and stored raw data in S3 in parallel Data Science Practicum: Insurance Data Analysis Nov 2018 - May 2019 · Created a new database containing all features required in the analysis by merging one claim table and one client table with linking tables, fussy matching, and natural language processing · Improved the evaluation system by selecting significant factors using generalized linear models of pure premium, claim frequency and claim severity in R Deep Learning: Real Time Emotional Expression Recognition Apr 2019 - May 2019 · Developed a webcam to catch real-time facial expression as an input and returned an output of a predicted emotion being expressed with 80% confidence based on VGG16 architecture in tensorflow.keras Data Visualization: Traffic Patterns in Manhattan Aug 2016 - Dec 2017 · Provided a dynamic overview of the traffic density distribution via a video demonstrating the change of hourly traffic flow on the map using Folium in Python · Proposed urban-planning advice based on innovated concept Meta-Path in traffic flow, which detected dense traffic areas with few outlets based on strongly connected components and Pascal’s Triangle Claudia Xu 310-622-2320 | [email protected] EDUCATION Northwestern University Evanston, IL Master of Science in Analytics Dec 2019 (Expected) • Expected Courses: Predictive Analytics, Database System, Data Mining, Java & Python Programming, Deep Learning, Analytics for Big Data, Text Analytics, Data Visualization

University of California at Los Angeles Los Angeles, CA Bachelor of Science in Applied Math; Minor in Statistics Sep 2014 - June 2018 • Cumulative GPA: 3.95/4.0 • Latin Honor: College of Letters & Science, UCLA—Summa Cum Laude • Relevant Courses: Probabilities, Mathematical Statistics, Statistical Models in Finance, Computational Statistics, Regression Models Skills R, C++, Python, Java, SQL, Excel Project Work Kaggle Gun Violence Competition, University of California at Los Angeles May 2018 • Performed explanatory analysis on gun violence data in LA to help predict the most likely factors that would contribute to future shootings • Implemented random forest, generalized additive models, and XGBoost models, and selected the best model based on the highest accuracy rate applied on the testing data in R

Financial Analysis of 30 Stocks, University of California at Los Angeles Apr 2018 • Calculated and plotted the composition of equal allocation portfolio, minimal risk portfolio • Traced out efficient frontier with and without short sales allowed • Implemented single index model, constant correlation model, and multigroup model • Evaluated portfolios by performing Fama’s decomposition, examining time plots of the performance of all portfolios compared to S&P 500, and calculating 99% 5-day VaR from Monte Carlo simulations

Financial Analysis of Senseonics Holdings Inc., University of California at Los Angeles Sep 2017-Nov 2017 • Carried out financial analysis of Senseonics Holdings Inc. by Nasdaq Dozen approach and SWOT analysis to see its growth potential in the future

Wine Quality Prediction Analysis, University of California at Los Angeles Nov 2017 • Developed a statistical model to predict the quality scores of wine based on chemicals properties using linear discriminant analysis, logistic regression, and anova analysis in R Relevant Experience Rongsheng Finance Leasing Co., Ltd Wuhan, China Intern Jul 2017 - Sep 2017 • Collected information about customers’ reactions towards launching a new project through online surveys • Created graphs about current profit, and developed a statistical model to assess which predictors are significant • Led meetings to discuss the prospects and possible risks of the project and put forward an initial proposal of finance lease

Wuhan Iron and Steel Group Finance Company Wuhan, China Intern Jun 2015- Jul 2015 • Proposed future stock investment through analyzing macroeconomic and microeconomics report in recent quarters given by major brokerages • Identified the most profitable industries using the financial software WIND

1 / 1 Nuo (Nora) Xu (310)717-3625 | [email protected] | https://www.linkedin.com/in/nuo-nora-xu/ ​

EDUCATION ​ Northwestern University Evanston, IL Master of Science in Analytics Expected December 2019 ● Cumulative GPA: 3.90/4.00 ​ ● Relevant Coursework: Deep Learning, Analytics Value Chain, Data Mining, Analytics for Big Data, Database, Text ​ Analytics, Predictive Analytics, Reinforcement Learning University of California Los Angeles Los Angeles, CA ​ ​ Bachelor of Science in Statistics with a Minor in Mathematics June 2018 Bachelor of Arts in Sociology ● Cumulative GPA: 3.72/4.00; Statistics Major GPA: 3.93/4.00 ​ ​ ​ ● Relevant Coursework: Data Analysis and Regression, Mathematical Statistics, Optimization, Linear Algebra, Numerical ​ Analysis, Machine Learning, Applied Probability, Statistical Models and Data Mining

SKILLS ​ Programming Skills: Python, SQL (Presto/MySQL/Hive), R, Spark, Hadoop, Java, HTML, MATLAB, JavaScript ​ Software Skills: Git, Latex, Tableau ​

PROFESSIONAL EXPERIENCES ​ Menlo Park, CA Data Scientist Intern June 2019 - September 2019 ● Explored send and thread attribution points in Messenger to understand thread creation and resurrection ● Gauged potential value for each attribution based on self-defined axes through PCA to make product recommendations ● Conducted user segmentation analysis on results by demographics/interfaces/markets ● Built a dashboard showcasing attribution trends over time and optimize the attribution pipeline logic Feldsted & Scolney Los Angeles, CA ​ Data Analyst Intern July 2017 - July 2018 ● Researched the pair trading strategy for predicting the spread series of certain stock portfolios ● Developed algorithm for identifying potential profitable pair candidates based upon time series and statistical arbitrage ● Tuned training parameters in algorithm and visualized daily output of portfolios of pair stocks using R ● Obtained the yearly rate of return from profitable pairs as about 20%

PROJECT EXPERIENCES ​ BP Regional Price Risk Chicago, IL Data Analyst Consultant September 2018 - June 2019 ● Constructed classification models to forecast outcome of commercial contract bidding and facilitate risk management ● Produced time series models to explain underlying seasonality and trend factors, and predict monthly margin profiles ● Generated an automated pricing analysis tool to enable a more efficient and standardized approach in evaluating contract bids Yelp Recommendation System Evanston, IL MSiA Student Research Blog April 2019 ● Implemented a hybrid approach of Collaborative Filtering and Content-Based Filtering to build a personalized restaurant recommender ● Article can be found here: https://sites.northwestern.edu/msia/2019/04/24/personalized-restaurant-recommender-system-using-hybrid-approach/

AWARDS ​ MSiA & ABC Supply 2019 Hackathon | First Place ​ ​ American Statistical Association DataFest 2018 at UCLA | Winner “Best Insight” ​ ​ American Statistical Association DataFest 2017 at UCLA | Honorable Mention “Best Use of External Data” ​ ​ Yiwei Zhang

217-341-0628 | [email protected] EDUCATION Northwestern University, Evanston, Illinois Expected: December 2019 • Master of Science in Analytics 3.85/4.00 University of Illinois at Urbana Champaign, Champaign, Illinois May 2018 • Bachelor of Science with honors and highest distinction in Statistics, Psychology Major GPA 3.93/4.00 • Minor in Business, Computer Science Cumulative GPA 3.89/4.00 SKILLS • Programming: Python, SQL, R, Java, Spark, Hadoop, Hive, SAS, C++, JavaScript, D3, HTML, DBMS, Tableau • Analytics: Machine Learning, Deep Learning, Data Mining, Natural Language Processing, Image Recognition, Optimization, Survival Analysis, Time Series, Predictive Analytics, S3, AWS, RDS, Flask • Languages: Chinese (Native), French (Beginner), Spanish (Beginner) WORK EXPERIENCE Deloitte Consulting LLP June 2019-August 2019 Business Technology Analyst Summer Scholar | Strategy and Analytics Chicago, IL • Streamlined project management system by optimizing progress visualizations to automatically incorporate new data and show updates; reduced time and labor cost and offered leadership clearer views of project execution • Centralized data from 5 testing units onto one platform; built executive dashboard and calculated crucial statistics to synthesize project progress; helped leadership identify delays and enhanced team coordination Wealth Engine Finance and Technology May 2018-August 2018 Data Science Intern | Customer Relation Management Beijing, China • Divided customer-company relationship into 4 lifecycles using Gaussian Mixture and Gradient Boosting on 70,000 customer data in Python; helped investment advisors maintain a healthy relationship with customers • Calculated customer churn probability and life value in stock market using Cox Hazards model; developed differentiated customer strategy based on their lifecycle, churn probability and life value to decrease leaving rate PROJECTS Principal What-If Analysis Portfolio Construction | Practicum Team Member September 2018-June 2019 • Systemized portfolio construction process by building construction and comparison prototype in RShiny through Agile development; helped portfolio managers compare key performance metrics and make scientific decisions • Optimized fund allocation engine using non-linear optimization in R; calculated ideal fund percentages under constraint to target asset mapping with least number of trades and money movement Fashion Image Matching Deep Learning Project | Project Team Member March 2019-June 2019 • Extracted the color and shape of each clothing item in Zara database using K-Means and Auto-encoder in Python • Found affordable substitutes for expensive items inputs using KNN with 73% decrease in training error and presented findings at the annual data science conference Analytics Exchange 2019 - Women in Data Science & AI YouTube Channel Subscriber Prediction | Individual Analyst March 2019–June 2019 • Predicted and visualized subscriber amount in 2, 5, 8 years within 5% error margin given channel features using XGBoost on 8M YouTube data in Python; identified young channels with potential growth and great market value • Created web app on Flask for user input and subscriber trend visualization; built pipeline from S3 to AWS RDS Venmo Transaction Classification | Individual Analyst May 2019 • Analyzed Venmo’s degree distribution on 100M data in PySpark to visualize trend in reciprocal transaction • Distinguished key features for transaction classification by conducting text mining on comments and emoji; classified and visualized transactions into 5 types for future customer strategy development using DBSCAN AWARDS Midwest Undergraduate Data Analytics Competition April, 2017 Team Leader and Top 5 Finalists Winona, MN • Led team of 4 to combine and analyze residential data in 5 datasets and predict churn probability using Random Forest and SVM in SAS and R in 24 hours; developed client stories on factors causing residents to leave • Presented insights on retaining customers through segmentation; ranked top 5 among 50 teams from 30 colleges INTERESTS • Traveling (Egypt, Sahara, Amazon Forest); wine-tasting (WSET certificate); Zheng (classical Chinese instrument) Yufei (Eileen) Zhang [email protected] | (312) 316-2836 | www.linkedin.com/in/eileen-z EDUCATION Northwestern University, McCormick School of Engineering Evanston, IL Master of Science in Analytics Dec 2019 • GPA: 3.93/4.00 Coursework: Big Data, Data Mining, Predictive Analytics, Analytics Value Chain, Deep Learning, Data Visualization

Carnegie Mellon University, Tepper School of Business Pittsburgh, PA Bachelor of Science in Business Administration; Additional major in Statistics May 2018 • GPA: 3.63/4.00 Coursework: Statistical Graphics and Visualization, Statistical Computing, Modern Regression, Advanced Method Data Analysis

SKILLS • Programming: Python, Java, JavaScript, R, Hive, SQL, HTML, D3, Tableau, Git, Spark, Hadoop, • Data Analysis: Machine Learning, Database Engineering, Imagine Recognition, Optimization, Text Mining

WORK EXPERIENCE TransUnion Chicago, IL Research and Consulting Intern June-Sept 2019 • Increased code efficiency 20% by streamlining current HQL script. Analyzed 200M+ credit data to generate consumer credit distribution and created 17 metrics to assess borrowing patterns among 9 lines of business. • Composed quarterly Industry Insight Report to visualize and summarize credit trends in the U.S. consumer lending industry based on the metrics composed in Hive. • Performed time series analysis and built seasonal ARIMA models to predict future 3 years’ quarterly credit bureau sales to identify potential growth and optimize KPI planning.

Marcum Bernstein & Pinchuk LLP New York, NY Advisory Intern July-Aug 2018 • Supported potential $100 million public offering by conducting audit assignment for Huanyou International Travel including confirmation letter assurance and revenue recognition tasks. • Increased social media following number by 10% in 5 weeks by building a multivariate regression model in R-studio to identify factors that influence the online article views for the firm’s social media accounts.

Deloitte Touche Tohmastsu Limited Beijing, China Audit Intern July 2017 • Selected and verified 600+ sample entries of CITCC’s book of accounts, including cash sales, interest income, accounts receivable, mortgage payments and dividend income to ensure the accuracy of transactions. • Conducted comparable analysis of the firm’s financial statements to identify potential reasons of abnormal bank accounts and other significant differences in the companies’ financial statements compared to past performances. YCP Holdings Ltd. Shanghai, China Consulting and Marketing Intern (“Rainbow Bird”: Japanese Early Childhood Education School Project) June-July 2016 • Led a store expansion project for Rainbow Bird and composed a proposal to the client based on the research of 5 competitor schools’ course structures, location selections and marketing strategies. • Improved client bookings 40% and revenues 20% by redesigning course structure and employee compensation policy.

PROJECTS Demand Forecasting Model Development - ABC Supply Co. Nov 2018-June 2019 • Performed demand classification for over 13,000 products by analyzing the buying patterns using ~1.6M financial data. • Conducted multiple time series analysis to identify the best predictive model within each demand category and forecast quarterly future demand for 1,300 products-plant combinations with accuracy higher than 80%. • Built interactive dashboard in Tableau to provide visualizations for branch managers to optimize inventory planning.

TensorFlow Image Processing - Deep Learning in Fashion April – June 2019 • Created a system that helps users find affordable substitutes for their choice of outfits using TensorFlow. • Built a CNN model and a K-Means model training on over 5000 pictures to learn the shape and extract the color of the input clothing items. • Fitted a KNN model to identify the most similar item of the user input images, successfully decreased the loss of the baseline model by 73.33%.

IOS Store App Rating Prediction April – June 2019 • Predicted IOS store application ratings with supervised learning methods including Random Forest and XGBoost, increased the accuracy by 30% compared to the baseline linear regression model. • Created interactive web app on Flask using HTML, JavaScript and Python, built the pipeline from S3 to AWS RDS.

INTERESTS • Traveling, Skiing, Fitness, Hip-Hop Dancing, Volunteering Yueying (Sharon) Zhang [email protected] | 847-909-3178 | www.linkedin.com/in/yueying-sharon-zhang

Education Northwestern University, Evanston, IL 12/2019 M.S. in Analytics GPA: 4.0/4.0 Coursework: Predictive Analytics, Data Mining, Data Visualization, Analytics for Big Data (Hadoop & Spark), Analytics Value Chain, Deep Learning ▪ ABC Supply Hackathon Second Place 05/2019

New York University Shanghai, Shanghai, China 05/2018 New York University, New York, NY Double Degree; B.A. in Economics; Minor in Mathematics, Data Science GPA: 3.94/4.0 ▪ Dean’s List for Academic Year 2015, 2016, 2017 ▪ 2017 U.S. Mathematical Contest in Modeling, Meritorious Winner (Top 10%) ▪ 2017-2018 China National Scholarship (Top 0.2%) Coursework: Advanced Econometrics, Machine Learning, Databases, Algorithms, Data Structure

Technical Skills Programming & Software: Python, MySQL, R, Excel VBA, Stata, Tableau, Java Data Science: Clustering, Boosting Tree, Neural Network, A/B testing

Projects Lifetime Value Segmentation, Chicago Botanic Garden 02/2019 – 06/2019 ▪ Utilized gradient boosting tree model to classify the Garden’s current audience into different segments to better target audience with higher potential revenue ▪ Built typing tool using Python Flask, SQL and html language for the Garden to type future consumers into identified segments Online Bookstore Promotion Prediction, Northwestern University 11/2018 – 12/2018 ▪ Implemented a two-step model fitting approach by first developing a logistic regression model to identify responders and second building a multiple regression model to predict purchases of responders using 25+ customer data in R ▪ Identified the customers who could generate the greatest revenue

Work Experience Blue Cross and Blue Shield of Illinois, Montana, New Mexico, Oklahoma & Texas Chicago, IL Data Scientist Intern 06/2019 – 08/2019 ▪ Utilized TF-IDF and Markov Chain to preprocess 10+ million claim line data for modeling ▪ Implemented LightGBM and LSTM model to predict the next procedure based on treatment path and diagnosis, achieving 100% increase in model accuracy compared to the baseline ▪ Identified and visualized anomalous providers using model reconstruction error in Tableau to help members receive equal or high-quality treatment with lower cost

TransUnion Chicago, IL Graduate Analytics Consultant 10/2018 – 05/2018 ▪ Cooperated with the Financial Service team to aggregate 10 datasets and engineer approximately 45 features for household classification model training ▪ Built gradient boosting tree model to predict the household relationship using 5+ million consumer records in R and assigned household id to each consumer using Python NetworkX for efficient marketing ▪ Identified empty nest and divorce events within households

Deloitte Consulting Shanghai, China Analyst Summer Intern, Dept of Risk Advisory 06/2018 – 09/2018 ▪ Built templates with automatic features including option pricing, cash flow discounting and stress testing using Excel VBA, reducing assessment time by over 30% ▪ Conducted analysis on model sensitivity and assessment results to assist bank in risk management Yucheng Zhu [email protected] | github.com/yzelac | (617) 678-3417 EDUCATION

Northwestern University Evanston, IL Master of Science in Analytics Anticipated December 2019 GPA: 3.95/4.00 Current Coursework: Reinforcement Learning, Text Analytics, Business Value from Analytics Relevant Coursework: Predictive Analytics, Analytics Value Chain, Deep Learning, Analytics for Big Data, Data Warehousing, Data Visualization, Data Mining, Java & Python Programming

Bachelor of Arts in Art History & Economics September 2015 - June 2018 GPA: 3.92/4.00; Magnum cum laude, Phi Beta Kappa, Dean’s List, Outstanding Art History Major

SKILLS

§ Programming: Python, R, Java (MapReduce), SQL, JavaScript (D3.js), C++, Bash, Racket § Tools: Git, Hadoop, Spark, TensorFlow, Stata, Tableau, Vertica, LaTeX, AWS, GCP, Intel AI DevCloud § Languages: Mandarin Chinese (Fluent), German (Basic), French (Basic)

PROFESSIONAL EXPERIENCE

Wayfair Boston, MA Web Analytics Intern – Content Recommendations June 2019 - August 2019 § Monitored and analyzed 8B+ records of new clickstream tracking data on non-product, non-sale-event across Wayfair U.S. using Vertica SQL and Python to quantify the impact of different messages on website performance and funnel metrics § Segmented customers at multiple levels to evaluate message engagement and identified customer sign-up paths to 5 services § Published 26 interactive Tableau dashboards and provided PMs with rule-based personalization strategies for AB testing

TransUnion Chicago, IL Data Science Consultant October 2018 - June 2019 § Developed models capable of predicting the probability of people belonging to the same household with 16M consumer pairs § Engineered 50+ predictive features using 9 data sets and performed feature selection and model training using XGBoost in R § Constructed matrices capturing relationships between consumer pairs and applied convolutional neural network (CNN) to classify “images” of households in Python § Implemented household aggregation at both primary address level and family level through edge classification and validated results based on manual review, rental inquiry data, and specific county data

Sotheby’s New York, NY Old Master Paintings & European Works of Art Intern June 2017 - August 2017 § Assisted specialists in market trends analysis, client support, consignments authentication, and archive research § Accomplished 2 single-owner valuation projects with a total of 220+ pieces of artwork independently § Initiated and completed 2 off-site research projects at the Metropolitan Museum of Art and the Frick Art Reference Library

PROJECT EXPERIENCE

Machine: The New Art Connoisseur (First Author, Manuscript in Preparation) March 2019 - Present § Conducted 9-class art style classification with 24k+ accurately labeled images of paintings using VGG-16, ResNet-152, Inception V3, and Inception-ResNet V2 without pre-trained weights on GPU using TensorFlow § Extracted features by adding a fully connected layer with 512 neurons before the softmax layers of the best-performing model based on Inception-ResNet V2, which achieved a state-of-the-art classification accuracy of 86.24% § Discovered clear chronological patterns of development among styles at painting level through 2D & 3D T-SNE visualizations § Performed network analysis using NetworkX and achieved both anticipated and currently non-obvious artist level linkages

Wine Quality Prediction Web Application (Available on GitHub) March 2019 - June 2019 § Designed and built a Flask app that allows users to predict the quality of a wine based on physiochemical properties § Implemented a fully reproducible Random Forest classification model with 93% testing accuracy based on 1.6k data instances § Produced scripts to acquire data and land in Amazon S3, build database tables locally or on Amazon RDS, and launch Flask app locally or on Amazon EC2

ACTIVITIES AND INTERESTS

BCG Gamma Hackathon (Chicago), Second Place Winner January 2019 Berlin: Global City in the Center of Europe, Program Participant at Humboldt-Universität zu Berlin June 2016 - August 2016 Interests: Film photography (medium & large format), wine (WSET Level 3 Award in Wines), cello, museums