Retail Analytics

2 Credits.

The retail and service sector is the largest of all economic activities and evolving rapidly in the age of big data and Artificial Intelligence. This course will leverage data-driven tools and theoretical models to analyze decisions of retail firms. We will cover a wide range of topics in strategic decisions in retailing: pricing, location, franchising, and omni-channel retailing. Using the real data in retailing, we will demonstrate and implement a wide range of statistical methods in econometrics and machine learning: single and multi-variate linear regressions, logistic regressions, classification trees, random forest, and multi-layer neural network. The focus is on predicting the effects of marketing decisions on profitability, although we will touch on causality as well. The questions this course will explore includes:How is the landscape of retailing changing in the age of Artificial Intelligence and big data?What is the right price and promotion in presence of competitors?How should a retailer choose a store location?How does omni-channel retailing influence the way shoppers move through all channels in their search and buying process?This class is practical and hands-on. All strategic decisions in business require a quantitative assessment of cause and effect. Each week we will introduce a new data set and data-driven tool that is valuable in the context of data scientists in retailing. You will learn how to perform convincing data analyses to answer specific questions. We will use R and ArcGIS for analyzing data. We do not assume that you have used R or ArcGIS, software for statistical and geographical analyses, respectively, in a previous class. For potential overlaps with other courses, we will cover them at a faster pace and emphasize techniques that are not covered in other courses.