Deloitte Analytics possible enhancements Contacts Having a sales predictive model is the first step towards creating a data-driven company. Alongside the predictive model, it is advisable to adopt a series of tools to support decisional business processes. Alfredo Maria Garibaldi Partner | Analytics Country Leader MONITORING TOOL [email protected] Building dashboards that visualize predicted Daniele Pier Giorgio Bobba results and comparisons with previous years Partner is a key tool for business users interested in [email protected] monitoring the actual performance of the company. Marco Leani Partner [email protected] Alberto Ferrario Director KPIs REPORTING [email protected] It is important to create a tool that gives users the possibility to analyze KPIs and detect misalignments or deviation from expected values or targets (e.g.: early-warning, alerts, traffic light charts…). PRESCRIPTIVE ANALYSIS Prescriptive Analytics extends beyond predictive analytics by specifying both the actions necessary to achieve predicted outcomes and the interrelated effects of each decision. This kind of analysis is able to answer questions such as “what do we need to do to achieve a specific forecast?” Our national team of over 200 professionals has proven experience in structuring, managing, and delivering Enterprise Information Management strategies and implementation services. Through the collective experience of local practice and leveraging TOOLS FOR DEVELOPING AND assets and best practices of our global WW Deloitte Analytics team, we have serve our REPORTING SALES FORECASTING customers with a broad array of toolkits, accelerators, models, leading-edge practices, diagnostics, and governance approaches to accelerate and improve the quality of EIM Deloitte Analytics has a vast knowledge of projects and ensure a focus on value creation. technical tools for data management, data Deloitte refers to one or more of Deloitte Touche Tohmatsu Limited, a UK private company modelling and reporting in Sales Forecasting. limited by guarantee (“DTTL”), its network of member firms, and their related entities. DTTL and each of its member firms are legally separate and independent entities. DTTL (also Access to relevant data-driven insights is a referred to as “Deloitte Global”) does not Sales forecasting necessity not only to formulate an effective provide services to clients. Please see www.deloitte.com/about for a more detailed business strategy, but also to monitor its description of DTTL and its member firms. Deloitte Analytics Approach execution. © 2018 Deloitte Consulting Srl The growing world Principles for a great Sales Forecast of data PROBLEM DEFINITION USE EXTERNAL DATA INVOLVE BUSINESS EXPERTS 1 Identify the main business goals and set expectations before any development phase. Robust predictions benefit from having Sales forecasting is not a one-time activity, high quality and easily accessible data. but an ongoing process that affects every Data has undoubtedly become the fuel for competitive These data can be enriched with external aspect of the sales pipeline. Therefore, it is DATA GATHERING & PREPARATION sources that can contribute improving the important not only to make predictions SETTING EXPECTATION Search and preprocess the data to define and advantage in the 21st century. quality of the predictions. Depending on based on the numbers on hand but also integrate the different data sources that will be Nowadays we generate and collect enormous volumes of data the product of the company, different to pair these numbers with qualitative 2 used as foundation for the models. and we are able to give machines the appropriate input for kinds of external data could be used. information in order to get a more realistic Data preparation is one of the most important and critical phases in a data mining project: data needs them to learn and predict outcomes by using algorithms to Below are some examples of open view of the business. This can be achieved external data: with appropriate communication and to be effectively interpreted and analysed. interpret raw data. • income-age geographical distribution collaboration between the business and • blogs or social networks the team involved in the construction of EXPLORATORY DATA ANALYSIS Why sales forecasting • articles the forecasting model. Primary analyses are carried out on data in order • macro-economic factors to use insights from results to define further steps. Sales forecasting allows companies to spot potential issues or risks and design appropriate • sector indexes COLLECTING INFORMATION 3 The KPIs that should be used in the machine corrective actions to mitigate them. learning models would be individuated and it 180 15% would be assessed how they are related to each other. 160 10% SALES DEMAND INVENTORY FINANCIAL 140 5% PLANNING PLANNING CONTROLS PLANNING MACHINE LEARNING 120 Sales forecasting helps The sales forecast is the The more accurate the Anticipating sales gives 0% The process of applying statistical algorithms on sales managers planning best way to get a good sales forecast, the better managers the 100 prepared dataset, providing a rigorous framework their future activities, estimate of the product prepared your company information they need to -5% 80 providing each of them demand. Sales teams are will be to manage its predict revenue and to test those models. -10% with a business plan for in the front line of inventory, avoiding both profit. Having good 60 4 Insights drawn from previous phases are used to managing their territory. business forecasting and overstock and stock-out forecasting information -15% Forecasting is the tool best positioned to gather situations. Stable gives a company the 40 choose the most appropriate models that could be that helps them identifing information about inventory also means ability to explore 20 -20% applied, evaluate pros and cons and implement the the necessary customers anticipated demand better management of possibilities to rise both MODELING INFORMATION solution. to meet their targets. your production revenue and net income 0 -25% M +1 M +2 M +3 M +4 M +5 M +6 M +7 M +8 M +9 M +10 DEVIATION REAL FORECAST VALIDATION & TESTING Assess models’ accuracy and robustness. As INTERNAL CONTINUOS GAIN MARKETING models are used to forecast future sales, they CONTROLS IMPROVEMENT INSIGHTS BENEFITS DEFINE CLEAR NEEDS BE FLEXIBLE TO CHANGE 5 should be generalized and be able to give reliable results outside of the dataset they have been Having an insight on the Continuous improvement Accurate sales Sales forecasting gives The key phase in creating a sales It is impossible to use a single model that projected production is a goal of many if not all forecasting can help you marketing an important forecasting solution is the understanding will ensure the track of the exact terms, developed on. rates gives the possibility businesses. By tracking data and gaining look at future sales. to have a better control forecasting sales and insights into areas where This offers the and the definition of the business needs: time, and context of every sale. Instead, of the internal continually revising improvements can be opportunity to schedule this allows to delimit the perimeter of what companies should focus on developing a RESULTS COMMUNICATION operations. By processes to increase made. Furthermore, it promotions if sales are is requested, what can be achieved and process that can be managed, re- Communicate effectively the advanced analytics anticipating future sales, accuracy, companies can can help understanding expected to be too weak managers can make improve all aspects of the customers’ behaviour how it can be achieved. Business evaluated, and modified as conditions 6 models results and translate them into actionable decisions about hiring, their business in order to increase knowledge is essential to define the most change. business insights. Models results should assist marketing and expansion performance conversion rates appropriate analytics tool. COMPARING EXPECTATIONS business in decision-making. The growing world Principles for a great Sales Forecast of data PROBLEM DEFINITION USE EXTERNAL DATA INVOLVE BUSINESS EXPERTS 1 Identify the main business goals and set expectations before any development phase. Robust predictions benefit from having Sales forecasting is not a one-time activity, high quality and easily accessible data. but an ongoing process that affects every Data has undoubtedly become the fuel for competitive These data can be enriched with external aspect of the sales pipeline. Therefore, it is DATA GATHERING & PREPARATION sources that can contribute improving the important not only to make predictions SETTING EXPECTATION Search and preprocess the data to define and advantage in the 21st century. quality of the predictions. Depending on based on the numbers on hand but also integrate the different data sources that will be Nowadays we generate and collect enormous volumes of data the product of the company, different to pair these numbers with qualitative 2 used as foundation for the models. and we are able to give machines the appropriate input for kinds of external data could be used. information in order to get a more realistic Data preparation is one of the most important and critical phases in a data mining project: data needs them to learn and predict outcomes by using algorithms to Below are some examples of open view of the business. This can be achieved external data: with appropriate communication and to be