Programme Multidisciplinary 2018 Data Sience EUROPEANEC Facets of CONFERENCE ON DATA ANALYSIS | GermanyDA 04 - 06 July Programme Chairs

Hans Kestler University of , Adalbert Wilhelm Jacobs University , Germany

Programme Committe

Stefan van Aelst KU Leuven, Belgium Casper Albers University of Groningen, Netherlands Martin Atzmüller Tilburg University, Netherlands Thomas Augustin LMU Munich, Germany Rolf Biehler , Germany Daniel Baier , Germany Bernd Bischl LMU Munich, Germany Ulf Brefeld Leuphana University of Lüneburg, Germany Claudio Conversano University of Cagliari, Italy Reinhold Decker , Germany Sebastian Destercke University of Technology of Compiègne (UTC), France Florian Dumpert University of Bayreuth, Germany Ralph Ewerth TIB, Leibniz Universität Hannover, Germany Mohsen Farid University of Derby, United Kingdom Peter Flach University of Bristol, United Kingdom Johannes Fürnkranz TU Darmstadt, Germany Michaela Geierhos Paderborn University, Germany Andreas Geyer-Schulz KIT Karlsruhe, Germany Daniel Guhl HU , Germany Barbara Hammer Bielefeld University, Germany Dominik Heider University of , Germany Christian Hennig University College London, United Kingdom Tadashi Imaizumi Tama University, Japan Salvatore Ingrassia Catania University, Italy Krzysztof Jajuga Wrocław University, Poland Wolfgang Konen TH Köln, Germany Georg Krempl Utrecht University, Netherlands Koji Kurihara Okayama University, Japan Berthold Lausen University of Essex, United Kingdom Xiaohui Liu Brunel University, United Kingdom Volker Lohweg Ostwestfalen-Lippe University of Applied Sciences, Germany Eneldo Loza Mencia TU Darmstadt, Germany Felix Mohr Paderborn University, Germany Angela Montanari University of Bologna, Italy Emmanuel Müller , Germany Fionn Murtagh University of Huddersfield, United Kingdom Mohamed Nadif Paris Descartes University, France Axel Ngonga Paderborn University, Germany Oliver Niggemann Ostwestfalen-Lippe University of Applied Sciences, Germany Friederike Paetz University of Clausthal, Germany Józef Pociecha Cracow University of Economics, Poland Niel le Roux Stellenbosch University, South Africa Lars Schmidt-Thieme University of , Germany Frank Scholze KIT Karlsruhe, Germany Carsten Schulte Paderborn University, Germany Jerzy Stefanowski Poznan University of Technology, Poland Kevin Tierney Bielefeld University, Germany Alfred Ultsch , Germany Maurizio Vichi Sapienza University of Rome, Italy Henning Wachsmuth Paderborn University, Germany Marcel Wever Paderborn University, Germany WEDNESDAY Auditorium Room 1 Room 2 Room 3 Room 4 Room 5 08:40-09:00 Opening

09:00-10:00 Plenary Talk Gurevych 10:00-10:30 Coffee Break Coffee Break Coffee Break Coffee Break Coffee Break Coffee Break

10:30-12:30 Interpretable Bioinformatics and Textual Data Analysis Consumer Web and Data Machine Learning for Machine Learning 1 Biostatistics and Digital Preferences and Science Dynamic Systems Humanities Marketing Analytics 12:30-14:00 Lunch Lunch Lunch Lunch Lunch Lunch

14:00-15:00 Semi-Plenary Talk Semi-Plenary Talk Semi-Plenary Talk Christmann Hartig Rocci 15:00-17:00 Interpretable Dimensionality Recommendation and Statistical and Big Data and Industrial Applications Machine Learning 2 Reduction e-Commerce Econometric Methods Complex Network Analytics 17:00-17:30 Coffee Break Coffee Break Coffee Break Coffee Break Coffee Break Coffee Break

17:30-18:30 Plenary Talk De Raedt

THURSDAY Auditorium Room 1 Room 2 Room 3 Room 4 Room 5 09:00-10:00 Plenary Talk Berger 10:00-10:30 Coffee Break Coffee Break Coffee Break Coffee Break Coffee Break Coffee Break

10:30-12:30 Comparison and Statistical Learning Computational Social Advances in Dim. Reduction and Mining Streaming Benchmarking of with Imprecision 1 Science Recursive Visualization for and Time-Evolving Cluster Analysis Partitioning and Classification 1 Data Methods Related Methods 12:30-14:00 Lunch Lunch Lunch Lunch Lunch Lunch

14:00-15:00 Semi-Plenary Talk Semi-Plenary Talk Hammer Couso Coffee Break Coffee Break Coffee Break Coffee Break Coffee Break Coffee Break

15:00-17:00 Clustering Statistical Learning Data Analysis in Machine Learning 1 Dim. Reduction and Time Series Analysis with Imprecision 2 Psychology and Visualization for and Online Mental Health Classification 2 Algorithms 18:00-20:00 Social Event Social Event Social Event Social Event Social Event Social Event

20:00-23:00 Conference Dinner Conference Dinner Conference Dinner Conference Dinner Conference Dinner Conference Dinner

FRIDAY Auditorium Room 1 Room 2 Room 3 Room 4 Room 5 09:00-10:00 Plenary Talk Beerenwinkel 10:00-10:15 Coffee Break Coffee Break Coffee Break Coffee Break Coffee Break Coffee Break

10:15-12:15 Machine Learning 2 Data Analysis Models Image and Music Applications 1 Multivariate, multi- Data Mining and in Economics and Data Analysis label, and ranking Knowledge Discovery Business data 12:15-13:15 Lunch Lunch Lunch Lunch Lunch Lunch

13:15-14:35 Multimodal Data and Data Analysis in Statistical EuADS Symposium 1 Algorithm Selection Statistical Aspects of Cross-Modal Finance 1 Visualization for and Configuration for Machine Learning 1 Relations Data Science Machine Learning 14:35-14:50 Coffee Break Coffee Break Coffee Break Coffee Break Coffee Break Coffee Break

14:50-16:10 Data Analysis in Applications 2 EuADS Symposium 2 Machine Learning Statistical Aspects of Finance 2 and Optimization Machine Learning 2 16:15-16:30 Farewell

3 Wednesday, 4-Jul-2018 08:40 – Opening session 09:00 Location: Auditorium 09:00 – Plenary talk: Iryna Gurevych 10:00 Disentangling the thoughts: Latest news in computational argumentation Location: Auditorium Chair: Henning Wachsmuth 10:00 – Coffee break 10:30 10:30 – Bioinformatics and Biostatistics 12:30 Location: Seminar room 1 Chair/Organizer: Dominik Heider 10:30 Ensemble Feature Selection for Regression Problems Ursula Neumann, Dominik Heider 10:50 Group-Wise Feature Selection with Stacked Domain Learning Wouter van Loon, Marjolein Fokkema, Botond Szabo, Mark de Rooij 11:10 Learning the Topology of Latent Signaling Networks from High Dimensional Transcriptional Intervention Effects Zahra Sadat Hajseyed Nasrollah, Achim Tresch, Holger Fröhlich 11:30 de.NBI Cloud - Compute Power for your Project Peter Belmann 11:50 Towards Enabling Virtual Clinical Studies with Longitudinal Bayesian Network Modeling Meemansa Sood, Akrishta Sahay, Reagon Karki, Martin Hofmann Apitius, Holger Fröhlich 12:10 Gaining New Knowledge on the Cell biological Processes of Cancer by Inter- pretable Machine Learning Alfred Ultsch

10:30 – Textual Data Analysis and Digital Humanities 12:10 Location: Seminar room 2 Chair/Organizer: Michaela Geierhos 10:30 Text Broom: A ML-based Tool to Detect and Highlight Privacy Breaches in Physician Reviews: An Insight into Our Current Work Frederik Simon Bäumer, Michaela Geierhos 10:50 Analyzing the Spectrum of Free Verse Poetry by using Digital Methods Burkhard Meyer-Sickendiek, Hussein Hussein, Timo Baumann 11:10 Big Data and Digital Humanities(?) Jochen Tiepmar 11:30 The FinderApp WiTTFind for Wittgenstein’s Nachlass Maximilian Hadersbeck, Alois Pichler, Sabine Ullrich, Ines Röhrer 11:50 Topic Detection and Classification in Consumer Web Communication Data Atsuho Nakayama

10:30 – Consumer Preferences and Marketing Analytics 12:30 Location: Seminar room 3 Chair/Organizer: Friederike Paetz, Daniel Guhl 10:30 Identifying Nested Preference Structures in Choice-Based Conjoint Analysis: A Simulation Study Nils Goeken, Peter Kurz, Winfried J. Steiner

4 10:50 Advertising for a Scientific Publishing Service in Social Media Networks: Ef- fects on Reach and Prominence. Victoria-Anne Schweigert, Andreas Geyer-Schulz 11:10 On the Effect of HB Covariance Matrix Prior Settings: A Simulation Study Maren Hein, Peter Kurz, Winfried J. Steiner 11:30 Dynamic Structural Equation Models of Momentary Assessments in Con- sumer Research Adam Sagan 11:50 Lexicographic Preferences in Customer Review Data Following a Criterion- Based Approach Michael Bräuning

10:30 – Web & Data Science 12:30 Location: Seminar room 4 Chair/Organizer: Axel Ngonga 10:30 A Simple and Fast Approach to Knowledge Graph Embedding Tommaso Soru, Stefano Ruberto, Diego Moussallem, Edgard Marx 10:50 CostFed: Cost-Based Query Optimization for SPARQL Endpoint Federation Alexander Potocki, Muhammad Saleem, Tommaso Soru 11:10 Benchmarking Cloud Services for the Internet of Things Kevin Grünberg, Wolfram Schenck 11:30 Sensitivity Analysis with FANOVA Graphs Sonja Kuhnt 11:50 Using Textual Features for Validating RDF Knowledge Bases Zafar Habeeb Syed, Michael Röder, Axel-Cyrille Ngonga Ngomo

10:30 – Machine Learning for Dynamic Systems 12:30 Location: Seminar room 5 Chair/Organizer: Volker Lohweg, Oliver Niggemann 10:30 Ensemble Methods for Tracking Various Concept Drift Structures Dhouha Mejri, Mohamed Limam, Claus Weihs 10:50 Structure Identification of Dynamical Takagi-Sugeno Fuzzy Models by Using LPV Techniques Matthias Kahl, Andreas Kroll 11:10 OpenCL Deep Learning Framework for Automated Text Recognition Patrick Kappen, Lester Kalms, Diana Goehringer 11:30 A Reinforcement Learning Strategy for the Swing-Up of the Double Pendulum on a Cart Michael , Julia Timmermann, Ansgar Trächtler, Eyke Hüllermeier 11:50 Development of a Concept for Process Improvement Based on Large Amount of Data Steffen Hovestadt 12:10 Behavioural Profiling of Industrial Assets Through Numerical Encoding of Event Logs Pierre Dagnely, Tom Tourwé, Elena Tsiporkova

5 10:30 – Interpretable Machine Learning 1 12:30 Location: Auditorium Chair/Organizer: Eneldo Loza Mencía, Johannes Fürnkranz 10:30 Cognitive Bias vs Inductive Bias: Use of Cognitive Heuristics in the Design of Machine Learning Algorithms Tomas Kliegr 10:50 Rule Editor for Cognitive Experiments: Towards Better Understanding of Rule Interpretability and Comprehension Stanislav Vojir, Patrik Kopecky, Tomas Kliegr 11:10 Interpretable Classification of Facial Expressions of Pain Michael Siebers, Ute Schmid, Dominik Seuss, Jens Garbas, Teena Hassan, Miriam Kunz, Stefan Lautenbacher 11:30 Interpretable Instance Based Text Classification for Social Science Research Projects - An Evaluation Helena Löfström, Tuwe Löfström, Ulf Johansson 11:50 How Interpretable are You? A Framework for Quantifying Interpretability Amit Dhurandhar

12:30 – Lunch break 14:00 13:00 – Museum tour 14:00 Location: Museum 14:00 – Semi-plenary talk: Johannes Hartig 15:00 Analysis of data from educational achievement tests with generalized linear mixed models Location: Seminar room 1 Chair: N.N. 14:00 – Semi-plenary talk: Roberto Rocci 15:00 Finite mixtures for simultaneous clustering and reduction of matrix value observa- tions Location: Seminar room 3 Chair: Christian Hennig 14:00 – Semi-plenary talk: Andreas Christmann 15:00 Kernel-based methods in machine learning Location: Auditorium Chair: Claus Weihs 15:00 – Dimensionality Reduction 17:00 Location: Seminar room 1 Chair/Organizer: Volker Lohweg 15:00 Comparing Two Brand Switching Matrices by Asymmetric Multidimensional Scaling Akinori Okada, Hiroyuki Tsurumi 15:20 Investigating Quality measurements of projections for the Evaluation of Dis- tance and Density-based Structures of High-Dimensional Data Michael Christoph Thrun, Alfred Ultsch 15:40 Knowledge Discovery from Low-Frequency Stream Nitrate Concentrations: Hydrology and Biology Contributions Michael Christoph Thrun, Lutz Breuer, Alfred Ultsch

6 16:00 On Extracting Asymmetric Changes in Asymmetric Matrices Tadashi Imaizumi 16:20 Multivariate Gaussian Feature Selection Helene Dörksen, Volker Lohweg 16:40 Choosing Among Notions of Depth for Multivariate Data Karl Mosler, Pavlo Mozharovskyi

15:00 – Recommendation and eCommerce 17:00 Location: Seminar room 2 Chair/Organizer: Daniel Baier 15:00 A Segmented Kano Perspective on the User Interface of Online Fashion Shops Daniel Baier, Alexandra Rese 15:20 Modeling Customer Journey Value: Predicting Customer Churn and Future Net Value Dominic Christian Pastoors, Daniel Baier 15:40 Two-mode Overlapping Clustering for Three-mode Data with Applications to Online Shopping and Site Engineering Atsuho Nakayama, Daniel Baier 16:00 Dynamic Prediction of Propensity to Purchase by Landmark Modelling Ilan Fridman Rojas, Aris Perperoglou, Berthold Lausen, Henrik Nordmark 16:20 Recommending Travel Itineraries using Social Media Radhika Gaonkar, Maryam Tavakol, Ulf Brefeld 16:40 Using Association Rules for Dynamic Updates of Personalized Recommenda- tions Nicolas Haubner

15:00 – Statistical and Econometric Methods 17:00 Location: Seminar room 3 Chair/Organizer: N.N. 15:00 Adaptive Confidence Intervals for Kinks in Regression Functions Viktor Bengs, Hajo Holzmann 15:20 The Non-Gaussian ESEMIFAR Model Yuanhua Feng, Sebastian Letmathe 15:40 Further Development of the Double Conditional Smoothing for Nonparametric Surfaces Under a Lattice Spatial Model Bastian Schäfer, Yuanhua Feng 16:00 Identifying the Most Relevant Information in Skewed Distributions Alfred Ultsch 16:20 Bernoulli Mixture Models as a Part of Credibility Theory Anne Sumpf 16:40 Observed versus Unobserved Heterogeneity in Structural Equation Models: Cross-Country Data on Virtual-Try Ons Alexandra Rese, Eleonora Pantano, Daniel Baier

15:00 – Big Data and Complex Network Analytics 17:00 Location: Seminar room 4 Chair/Organizer: Martin Atzmüller 15:00 A New Approach to Measuring Distances in Dense Graphs Fatimah Almulhim, Peter Thwaites, Charles Taylor

7 15:20 The Impact of Graph Symmetry on Clustering Fabian Ball, Andreas Geyer-Schulz 15:40 Scalable Knowledge Graph Exploration for Sentiment Classification Gezim Sejdiu, Ali Denno, Mohamad Denno, Hajira Jabeen, Jens Lehmann 16:00 Comparing Partitions of the Petersen Graph Andreas Geyer-Schulz, Fabian Ball 16:20 Graph-Theoretic Network Analysis of the Interactions Between Patients, Physicians and Prescribed Drugs Reinhard Schuster, Timo Emcke 16:40 Traffic Flow Analysis Using 12 Years of Data Ian Marsh

15:00 – Industrial Applications 17:00 Location: Seminar room 5 Chair/Organizer: N.N. 15:00 Data and Model Management Architecture for the Steel Industry David Arnu, Fabian Temme, Edwin Yaqub, Gabriel Fricout, Marcus Neuer 15:20 Unsupervised Learning Approach to Assign Error Types to Automobile En- gine Failures Shailesh Tripathi, Sonja Strasser, Lukas Schimpelsberger, Matthias Dehmer 15:40 Applications of Machine Learning and Predictive Analytics in the Automotive Industry Ralf Klinkenberg 16:00 Development of a Data-Driven Software Tool to Detect Optimal Electrode Sheets in Lithium-Ion Battery Production Oliver Meyer, Claus Weihs, Sarah Schnackenberg, Michael Kirchhof 16:20 Automated Prediction of Assembly Plans for New 3D Product Designs Ralf Klinkenberg

15:00 – Interpretable Machine Learning 2 17:00 Location: Auditorium Chair/Organizer: Eneldo Loza Mencía, Johannes Fürnkranz 15:00 Explanation Methods in Deep Neural Networks: An Overview Gabrielle Ras, Marcel van Gerven, Pim Haselager 15:20 A Manifold Perspective for Debugging and Interpreting Deep Learning Models Ning Xie, Derek Doran 15:40 Rule Extraction from a Convolutional Neural Network in Sentiment Analysis Guido Bologna 16:00 Rule Extraction with Guarantees Ulf Johansson, Henrik Boström, Cecilia Sönströd 16:20 Understanding Learned Models by Identifying Important Feature Frontiers Mark Craven, Kyubin Lee, Sid Kiblawi, Akshay Sood 16:40 Explaining Random Forest Predictions using Frequent Itemset Mining Henrik Boström, Ram Gurung, Tony Lindgren, Ulf Johansson

16:00 – Museum tour 17:00 Location: Museum 17:00 – Coffee break 17:30

8 17:30 – Plenary talk: Luc de Raedt 18:30 Can we automate data science? Location: Auditorium Chair: Hans Kestler

9 Thursday, 5-Jul-2018 09:00 – Plenary talk: James Berger 10:00 Gaussian process emulation of computer models with massive output Location: Auditorium Chair: Adalbert Wilhelm 10:00 – Coffee break 10:30 10:30 – Statistical Learning with Imprecision 1 12:10 Location: Seminar room 1 Chair/Organizer: Thomas Augustin, Sébastien Destercke 10:30 Learning Range-Query Predictors Vitalik Melnikov, Eyke Hüllermeier 10:50 Using Polynomial Errors-in-Variables Regression to Analyse Sequential Pro- cess Chains Oliver Meyer, Claus Weihs 11:10 Partial Relational Clustering : A Thresholding Approach Marie-Hélène Masson, Benjamin Quost, Sébastien Destercke 11:30 Issues in the Context of Missing Values Martin Spiess, Daniel Salfran 11:50 Relational Data Analysis for Weakly Structured Information: Utilizing Linear and Binary Programming for Computing Supremum Statistics on Closure Systems Georg Schollmeyer, Christoph Jansen, Thomas Augustin

10:30 – Computational Social Science 12:30 Location: Seminar room 2 Chair/Organizer: Henning Wachsmuth 10:30 Minorities in Social Networks Claudia Wagner 10:50 Community Analysis based on linguistic characteristics in Social Networks Kristi Lubonja, Mirco Schönfeld 11:10 Reputation through Observation: Active Lurkers in Online Communities Clemens Niemeyer, Mirco Schönfeld 11:30 (Automated) Text Analysis of German Online Participation Projects with an Interdisciplinary Approach from Computer Science and Communication and Media Studies Matthias Liebeck, Katharina Esau 11:50 A Practical Approach to Tackling Fake News Martin Potthast 12:10 Discourse Analysis as an Information Retrieval Problem Tim Gollub, Henning Schmidgen, Benno Stein

10:30 – Advances in Recursive Partitioning and Related Methods 12:30 Location: Seminar room 3 Chair/Organizer: Claudio Conversano 10:30 Visual Pruning for Informative Prediction Trees Roberta Siciliano, Antonio D’Ambrosio, Carmela Iorio, Giuseppe Pandolfo 10:50 Semisupervised Clustering through Recursive Partitioning and Complex Net- works Claudio Conversano, Giulia Contu, Luca Frigau, Francesco Mola

10 11:10 Boosted Decision Trees for Behaviour Mining of Concurrent Programs Com- binated with Genetic Algorithms Hana Pluháčková, Tomáš Vojnar, Bohuslav Křena 11:30 A Framework for Measuring Stability of Recursive Partitioning Methods Michel Phillip, Thomas Rusch, Carolin Strobl, Kurt Hornik 11:50 Distributional Regression Forests for Probabilistic Modeling and Forecasting Lisa Schlosser, Torsten Hothorn, Heidi Seibold, Achim Zeileis 12:10 Treatment Subgroup Interactions and Personalized Treatment Effects Heidi Seibold, Achim Zeileis, Torsten Hothorn

10:30 – Dimension Reduction and Visualisation for Classification 1 12:30 Location: Seminar room 4 Chair/Organizer: Niël le Roux 10:30 Forward Stagewise Linear Regression for Ensemble Methods Daniel Uys 10:50 Sum Score as Latent Variable for Sparse Multivariate Binary Data Vartan Choulakian, Jacques Allard 11:10 Visualising Incomplete Data with Subset Multiple Correspondence Analysis Johané Nienkemper-Swanepoel, Niël Le Roux, Sugnet Gardner-Lubbe 11:30 Model Selection for Projected Divisive Clustering David Hofmeyr, Nicos Pavlidis 11:50 Unravelling Black Box Machine Learning Technique Predictions using Biplots

Adriaan Rowan, Sugnet Gardner-Lubbe, Francesca Little 12:10 Detecting Disease Subtypes by Means of Cluster Independent Component Analysis (C-ICA) of Multi-Subject Brain Data Jeffrey Durieux, Tom F. Wilderjans

10:30 – Mining Streaming and Time-Evolving Data 12:30 Location: Seminar room 5 Chair/Organizer: Barbara Hammer, Georg Krempl, Jerzy Stefanowski 10:30 A General Extension for Online Discriminant Analysis Methods for Data Streams with Concept Drift Sarah Schnackenberg, Uwe Ligges, Claus Weihs 10:50 Temporal Density Extrapolation in Data Streams with Basis Expansion and Compositionally Modelled Coefficients Dominik Lang, Vera Hofer 11:10 Scalable Implementation of Dynamic Factor Machine Learning for Very High Dimensional Forecasting, Gianluca Bontempi 11:30 Improving Predictions of Polarities of Entity-Centered Documents using Entity-Centered Multinomial Naive Bayes Christian Beyer, Uli Niemann, Vishnu Unnikrishnan, Eirini Ntoutsi, Myra Spiliopoulou 11:50 Improving Feature Selection for Multinomial Naive Bayes Classifiers Over Tex- tual Streams Damianos Melidis, Eirini Ntoutsi 12:10 Analysis of Patient Evolution on Time Series of Different Lenghts Vishnu Unnikrishnan, Rüdiger Pryss, Thomas Probst, Manfred Reichert, Winnfried Schlee, Berthold Langguth, Myra Spiliopoulou

11 10:30 – Comparison and Benchmarking of Cluster Analysis Methods 12:50 Location: Auditorium Chair/Organizer: Christian Hennig 10:30 The Threats and Traps in Benchmarking of Cluster Analysis Methods Andrzej Dudek, Marcin Pełka, Marek Walesiak 10:50 Some Thoughts on Simulation Studies to Compare Clustering Methods Christian Hennig 11:10 Towards Automatic Assessment of Clustering Quality Andrey Filchenkov, Sergey Muravyov 11:30 Towards Evidence-Based Computational Statistics: Lessons from Clinical research on the Role and Design of Real-Data Benchmark Studies Anne-Laure Boulesteix, Rory Wilson, Alexander Hapfelmeier 11:50 Estimating the Quality of an Optimal Treatment Regime Aniek Sies, Iven Van Mechelen 12:10 External Validity Indices and Cluster Size Imbalance Matthijs Warrens 12:30 Benchmarking Cluster Analysis Methods using PDE-Optimized Violin Plots Michael Christoph Thrun, Felix Pape, Alfred Ultsch

12:30 – Lunch break 14:00 13:00 – Museum tour 14:00 Location: Museum 14:00 – Semi-plenary talk: Inés Couso 15:00 Maximum likelihood estimation from coarse data: what do we maximise? Location: Seminar room 3 Chair: Sebastian Destercke 14:00 – Semi-plenary talk: Barbara Hammer 15:00 Transfer learning and learning with concept drift Location: Auditorium Chair: Eyke Hüllermeier 15:00 – Coffee break 15:15 15:15 – Statistical Learning with Imprecision 2 16:35 Location: Seminar room 1 Chair/Organizer: Thomas Augustin, Sébastien Destercke 15:15 Density Estimation with Imprecise Kernels: Application to Classification Sébastien Destercke, Guillaume Dendievel 15:35 Estimation of an Imputation Model for Non-Ignorable Binary Missing Data Angelina Hammon 15:55 Reliable Multi-class Classification based on Pairwise Epistemic and Aleatoric Uncertainty Vu-Linh Nguyen, Sébastien Destercke, Marie-Hélène Masson, Eyke Hüllermeier 16:15 How Valid is MAR Imputation under MNAR: Some Insights from Educational Research Sabine Zinn

12 15:15 – Data Analysis in Psychology and Mental Health 17:35 Location: Seminar room 2 Chair/Organizer: Fionn Murtagh, Mohsen Farid 15:15 Depression Diagnosis using Deep Convolutional Neural Networks Mofassir ul Islam Arif, Maurício Camargo, Jan Forkel, Guilherme Holdack, Rafael Rêgo Drumond, Nicolas Schilling, Tilman Hensch, Ulrich Hegerl, Lars Schmidt-Thieme 15:35 Mental Health: Analytical Focus and Contextualization for Deriving Mental Capital Fionn Murtagh 15:55 Gaussian Process Panel Modeling – Kernel-Based Analysis of Longitudinal Data Julian Karch, Andreas Brandmaier, Manuel Voelkle 16:15 Linking Data and Psychological Theory with Process-based Models and Bayesian Data Analysis Alexander Krüger, Jan Tünnermann, Ingrid Scharlau 16:35 Probabilistic Time Series Clustering by Vector Autoregressive Metric Anja Ernst, Casper Albers, Marieke Timmerman 16:55 Health Shocks and Cognitive Decline in Older Ages Hendrik Schmitz 17:15 The Default Mode Revolution and Computational Psychoanalysis: Implica- tions for Future Health Research. Miloš Borozan, Rosapia Lauro Grotto

15:15 – Machine Learning 1 17:15 Location: Seminar room 3 Chair/Organizer: Hans Kestler 15:15 A Comparison of Automatic Algorithms for Occupation Coding Malte Schierholz 15:35 Stopping Criteria for Active Learning with a Robot Marek Herde, Adrian Calma, Daniel Kottke, Bernhard Sick, Maarten Bieshaar 15:55 Evaluating Ordinal Classifiers on Repetitive Class Structures Lisa Schäfer, Hans A. Kestler, Ludwig Lausser 16:15 Leela Chess Zero: A Crowd-Sourced Effort to Replicate and Improve Alp- haZero Folkert Huizinga, Karlson Pfannschmidt 16:35 Extraction of Classification Rules Using a Bee Swarm Approach Sadjia Benkhider

15:15 – Dimension Reduction and Visualisation for Classification 2 17:15 Location: Seminar room 4 Chair/Organizer: Niël le Roux 15:15 Supervised Feature Selection and Global Sensitivity Analysis Hana Sulieman, Ayman Alzaatreh 15:35 A Biplot based on a Principal Surface Raeesa Ganey, Sugnet Gardner-Lubbe 15:55 The Alpha-Procedure and Aspects of Selection of Classification Space Tatjana Lange 16:15 Computing Neural Reliability from EEG Recordings Pieter Schoonees, Niël Le Roux

13 16:35 Dimension Reduction Could be Used to Build Stable Models to Predict Sexual Activity Amongst Incoming First-Year Students Humphrey Brydon, Retha Luus, Rénette Blignaut, Innocent Karangwa, Joachim Jacobs 16:55 Classification Based on Dissimilarities Towards Prototypes Beibei Yuan, Willem Heiser, Mark de Rooij

15:15 – Time Series Analysis and Online Algorithms 17:15 Location: Seminar room 5 Chair/Organizer: Wolfgang Konen 15:15 Time Series Study on Job Market Demand using Co-Word Analysis Elisa Margareth Sibarani, Simon Scerri 15:35 Online Adaptable Time Series Anomaly Detection with Discrete Wavelet Trans- forms and Multivariate Gaussian Distributions Markus Thill, Wolfgang Konen, Thomas Bäck 15:55 Comparison of Machine Learning Approaches for Time-Series Based Quality Monitoring of Resistance Spot Welding Baifan Zhou, Tim Pychynski, Markus Reischl, Ralf Mikut 16:15 Music Generation with Long Short Term Memory Amin Dada, Rolf P. Würtz 16:35 An Experimental Evaluation of Time Series Classification Using Various Dis- tance Measures Paweł Piasecki, Tomasz Górecki 16:55 Using Time Series Analysis for Predicting Hemodynamic Instability in Inten- sive Care Patients Daniela Behnam, Mark Last

15:15 – Clustering 17:15 Location: Auditorium Chair/Organizer: Alfred Ultsch 15:15 Ensemble Clustering for Symbolic Data for Green Growth Analysis Marcin Pełka 15:35 The Performance of Tube Distance in Clustering Tasks Andrzej Sokołowski, Małgorzata Markowska, Sabina Denkowska 15:55 Two-Step Clustering of Micro Panel Data Maria Stachova, Lukas Sobisek 16:15 A Proposal of a New PAM-Like Clustering Algorithm for Symbolic Data Marcin Pełka, Andrzej Dudek 16:35 On the Selection Uncertainty in Parametric Clustering Alessandro Casa, Luca Scrucca, Giovanna Menardi

16:00 – Museum tour 17:00 Location: Museum 18:00 – Walk to Conference Dinner / Bus Transit 19:30 20:00 – Conference Dinner 23:00

14 Friday, 6-Jul-2018 09:00 – Plenary talk: Nico Beerenwinkel 10:00 Analyzing molecular tumor profiles for precision oncology Location: Auditorium Chair: Berthold Lausen 10:00 – Coffee break 10:15 10:15 – Data Analysis Models in Economics and Business 12:15 Location: Seminar room 1 Chair/Organizer: Józef Pociecha 10:15 Data Mining Models in Evaluation the Importance of Financial Indicators for Firms’ Financial Condition Assessment Józef Pociecha 10:35 Foreign Trade Effects on Regional Growth in Ukraine Victor Shevchuk 10:55 An Approach towards a Decentralized and Forecast-based Energy Trading Model Moritz Mönning, Gerrit Schumann 11:15 Context-Sensitive Performance Benchmarking of a Portfolio of Industrial As- sets Alessandro Murgia, Elena Tsiporkova, Mathias Verbeke, Tom Tourwe 11:35 Automatic Monitoring System for the Competency Gap Evaluation at the Rus- sian and Polish Labour Market Sergey Belov, Ivan Kadochnikov, Paweł Lula, Renata Oczkowska, Katarzyna Wójcik, Petr Zrelov

10:15 – Image and Music Data Analysis 12:15 Location: Seminar room 2 Chair/Organizer: Igor Vatolkin 10:15 Enhancing Flood Risk Analysis using Interactive Retrieval of Social Media Images Björn Barz, Bin Yang, Kai Schröter, Moritz Münch, Andrea Unger, Doris Dransch, Joachim Denzler 10:35 Handwritten Formula Recognition with Pixel-Wise Generative Adversarial Net- works Matthias Springstein, Clemens Pollak, Ralph Ewerth 10:55 Visual Stylometry of Comics Using CNN Features Jochen Laubrock, David Dubray 11:15 Measurement of Robustness of Features and Classification Models on De- graded Data Sets in Music Classification Igor Vatolkin 11:35 Classifying Music Genres Using Image Classification Neural Networks Alan Kai Hassen, Hilko Hermann Janßen, Dennis Assenmacher, Mike Preuß 11:55 Multi-Objective Optimization of Tone Onset Detection and Pitch Estimation Algorithms Kerstin Wintersohl, Nadja Bauer, Daniel Horn, Claus Weihs

15 10:15 – Applications 1 12:15 Location: Seminar room 3 Chair/Organizer: Mark Last 10:15 HMM with Non-Emitting States for Map Matching Wannes Meert, Mathias Verbeke 10:35 Automating Time Series Feature Engineering for Activity Recognition from Synchronized Inertial Measurement Units Andreas W. Kempa-Liehr, Jonty Oram, Thor Bezier 10:55 The Moderating and Mediating Role of Meaning of Work – a PLS Path Analysis Joachim Schwarz, Heiko Weckmüller 11:15 The Effect of Ambient Light Conditions on Road Safety Valentin Schiele, Christian Bünnings

10:15 – Multivariate, multi-label and ranking data 12:15 Location: Seminar room 4 Chair/Organizer: Eyke Hüllermeier 10:15 Using Multi-Label Logistic Regression to Maximize Macro F-measure Masaaki Okabe, Jun Tsuchida, Hiroshi Yadohisa 10:35 R-Vine Mixture Model for Modeling Multivariate Count Data Marta Nai Ruscone 10:55 A Representation of the Relationship Between Variables in Quantitative and Qualitative Mixed Data Mako Yamayoshi, Jun Tsuchida, Hiroshi Yadohisa 11:15 Learning to Rank based on Analogical Reasoning Mohsen Ahmadi Fahandar, Eyke Hüllermeier 11:35 Ranking Distributions based on Noisy Sorting Adil El Mesaoudi-Paul, Robert Busa-Fekete, Eyke Hüllermeier

10:15 – Data Mining and Knowledge Discovery 12:15 Location: Seminar room 5 Chair/Organizer: Andreas Geyer-Schulz 10:15 Swarm Data Mining for Energy Harvesting in the Boundary Layer of the Atmo- sphere Alfred Ultsch 10:35 Adaptation of Boosting Algorithm for Classification in Imbalanced Datasets Aouatef Mahani, Ahmed Riadh Baba Ali 10:55 Sparsity-Inducing Fuzzy Subspace Clustering Arthur Guillon, Marie-Jeanne Lesot, Christophe Marsala 11:15 Process Mining on Machine Event Logs for Profiling Abnormal Behavior and Root Cause Analysis Jonas Maeyens, Annemie Vorstermans, Mathias Verbeke 11:35 Patient Similarity Analysis for Personalized Health Prediction Models Araek Tashkandi, Nicole Sarna, Lena Wiese

10:15 – Machine Learning 2 12:15 Location: Auditorium Chair/Organizer: Peter Flach 10:15 Learning Choice Functions Karlson Pfannschmidt, Pritha Gupta, Eyke Hüllermeier

16 10:35 Data Augmentation for Discrimination Prevention Vasileios Iosifidis, Eirini Ntoutsi 10:55 Label Noise Filtering based on Cluster Validation Measures Veselka Boeva, Lars Lundberg, Jan Kohstall, Milena Angelova 11:15 A Forest of Stumps Amirah Alharthi, Charles Taylor, Jochen Voss 11:35 On the Projection of Machine Learning Scores to Well-Calibrated Probability Estimates Johanna Schwarz, Dominik Heider

11:00 – Museum tour 12:00 Location: Museum 12:15 – Lunch break 13:15 13:15 – Data Analysis in Finance 1 14:35 Location: Seminar room 1 Chair/Organizer: Krzysztof Jajuga 13:15 Mixture Models in Competing Risks Analysis. Application to Credit Risk As- sessment Ewa Wycinka, Tomasz Jurkiewicz 13:35 Residual Based Consistent Bubble Detection Leopold Sögner 13:55 Forecasting Non-Negative Financial Processes Using Different Parametric and Semi-Parametric ACD-Type Models Sarah Forstinger, Yuanhua Feng, Christian Peitz 14:15 Taxonomy of Risk on Metal Market Dominik Krężołek, Grażyna Trzpiot

13:15 – Statistical Visualization for Data Science 14:35 Location: Seminar room 2 Chair/Organizer: Koji Kurihara, Adalbert Wilhelm 13:15 Visual Support for Imbalanced Classification Adalbert Wilhelm 13:35 Visualization of Cluster Detection Based on Hierarchical Structure for Geospa- tial Data and Its Application Fumio Ishioka, Shoji Kajinishi, Koji Kurihara 13:55 Development of an Interactive Visualization System to Analyze the Influence of Drug Resistance Appearance Sanetoshi Yamada, Yoshiro Yamamoto, Kazuo Umezawa 14:15 Empirical Study on Analysis of Unauthorized-Access Log Data and its Visual Output Hiroyuki Minami

13:15 – European Association for Data Science (EuADS) Symposium on Data Science Ed- ucation 1 14:35 Location: Seminar room 3 Chair/Organizer: Rolf Biehler, Reinhold Decker, Peter Flach, Berthold Lausen, Carsten Schulte 13:15 The Project “ExWoSt Digitale Lernlabore”: Smart Data Labs as a Method of Data Science Education Katharina Schüller, Katrin Grimm

17 13:35 Statistical Computing and Data Science in Introductory Statistics Karsten Luebke, Matthias Gehrke, Norman Markgraf 13:55 From Computer Science and Statistics towards Data Science at LMU Munich Thomas Seidl, Göran Kauermann 14:15 Data Science and Big Data in Upper Secondary Schools: What Should Be Discussed from a Statistics Perspective? Rolf Biehler, Daniel Frischemeier, Susanne Podworny, Thomas Wassong

13:15 – Algorithm Selection/Configuration and Machine Learning 14:35 Location: Seminar room 4 Chair/Organizer: Bernd Bischl, Felix Mohr, Marcel Wever 13:15 Multi-Objective Selection of Algorithm Portfolios over Multiple Data Sets Daniel Horn, Rosa Pink 13:35 Predicting Rankings of Classification Algorithms in AutoML Helena Graf, Marcel Wever, Felix Mohr, Eyke Hüllermeier 13:55 Challenges of Meta-Learning on a Distributed Machine Learning Platform Christian Geißler 14:15 ML-Plan: Automated Machine Learning for Multi-Class and Multi-Label Clas- sification Felix Mohr, Marcel Wever, Eyke Hüllermeier

13:15 – Statistical Aspects of Machine Learning Methods 1 14:35 Location: Seminar room 5 Chair/Organizer: Florian Dumpert 13:15 Consistency and Robustness Properties of Predictors Based on Locally Learned SVMs Florian Dumpert 13:35 Classification in High Dimensions: When Are Rules Beneficial? Claus Weihs 13:55 Data-Driven Robust Control Using Reinforcement Learning Phuong Ngo, Fred Godtliebsen

13:15 – Multimodal Data and Cross-modal Relations: Analytics and Search 14:35 Location: Auditorium Chair/Organizer: Ralph Ewerth 13:15 Combining Textual and Visual Stylometry in the Analysis of Graphic Narrative Rita Hartel, Alexander Dunst 13:35 Applying Frequent Pattern Mining to Multimodal Behavior in Interaction: Vi- sualizing Significant Patterns Katharina Rohlfing, Marcel Ruland, Sascha Henzgen 13:55 Using Voronoi-Cells to Assess Action Efficacy in High-Performance Soccer Robert Rein, Daniel Memmert 14:15 Towards Analytics of Relations between Scientific Publications and Related Software Implementations Anett Hoppe, Jascha Hagen, Helge Holzmann, Günter Kniesel, Ralph Ewerth

14:35 – Coffee break 14:50

18 14:50 – Data Analysis in Finance 2 16:10 Location: Seminar room 1 Chair/Organizer: Krzysztof Jajuga 14:50 Joint Input and Predictive Model Parameters Selection for Financial Forecast- ing Iaroslav Shcherbatyi, Wolfgang Maass 15:10 A Box-Cox Semiparametric Multiplicative Error Model Xuehai Zhang, Yuanhua Feng 15:30 Model Risk of Selected Systemic Risk Measures for Polish Banking Industry Katarzyna Kuziak, Krzysztof Piontek 15:50 The Effects of the Regulatory Capital Requirements of Basel III on the Cost of Capital of Banks – an Empirical Analysis. Florian Naunheim, Matthias Gehrke, Jeffrey Heidemann

14:50 – Applications 2 16:10 Location: Seminar room 2 Chair/Organizer: N.N. 14:50 Sociohistorical Recommendations for the Dewey Decimal Classification Edi- torial Policy Committee for the Reclassification of Pentecostalism Adam Stewart 15:10 Multidimensional Comparative Ranking of the European Union Countries in the Area of Sustainable Development Marcin Pełka, Tomasz Bartłomowicz 15:30 Radiocarbon Dating of the Turin Shroud: New Evidence from Raw Data Tristan Casabianca, Benedetto Torrisi, Giuseppe Pernagallo, Emanuela Marinelli

14:50 – European Association for Data Science (EuADS) Symposium on Data Science Ed- ucation 2 15:50 Location: Seminar room 3 Chair/Organizer: Rolf Biehler, Reinhold Decker, Peter Flach, Berthold Lausen, Carsten Schulte 14:50 Digitally Fit?: Applied Machine Learning Academy for Industry Ralph Ewerth, Marc Dittrich, Wolfgang Nejdl, Claudia Niederee, Hendrik Noske, Jan- Hendrik Zab, Sergej Zerr 15:10 Data Science and Big Data in Upper Secondary Schools: What Should Be Discussed from a Perspective of Computing Education? Birte Heinemann, Lea Budde, Carsten Schulte 15:30 Industrial Data Science: Developing a Qualification Concept for Machine Learning in Industrial Production Nadja Bauer, Malte Jastrow, Daniel Horn, Lukas Stankiewicz, Kristian Kersting, Jochen Deuse, Claus Weihs

14:50 – Machine Learning and Optimization 16:10 Location: Seminar room 4 Chair/Organizer: Kevin Tierney 14:50 A Branch and Bound Algorithm for Decision Trees with Optimal Cross-Splits Ferdinand Bollwein, Martin Dahmen, Stephan Westphal 15:10 Deep Learning Assisted Heuristic Tree Search for the Container Premar- shalling Problem André Hottung, Shunji Tanaka, Kevin Tierney

19 15:30 Gaussian Process Emulation of Computer Experiments with Both Continuous and Categorical Inputs Dominik Kirchhoff 15:50 A First Analysis of Kernels for Kriging-based Optimization in Hierarchical Search Spaces Martin Zaefferer, Daniel Horn

14:50 – Statistical Aspects of Machine Learning Methods 2 16:10 Location: Seminar room 5 Chair/Organizer: Florian Dumpert 14:50 Factor Selection and Tests for Independence of Nominal and Metric Variates, Marked Rank Statistics Ulrich Müller-Funk, Stefanie Weiß 15:10 On the Influence of Margin Conditions on Rates of Localized Algorithms Ingrid Blaschzyk 15:30 Parallelizing Spectral Algorithms Nicole Mücke, Gilles Blanchard

16:15 – Farewell 16:30 Location: Seminar room 3

20