Search results

This case, along with its B case (UVA-QA-0865), is an effective vehicle for introducing students to the use of machine-learning techniques for classification. The specific context is predicting customer retention based on a wide range of customer attributes/features. The specific techniques could include (but are not limited to): regressions (linear and logistic), variable selection (forward/backward and stepwise), regularizations (e.g., LASSO), classification and regression trees (CART), random forests, graduate boosted trees (xgboost), neural networks, and support vector machines (SVM).

The case is suitable for an advanced data analysis (data science, machine learning, and artificial intelligence) class at all levels: upper-level business undergraduate, MBA, EMBA, as well as specialized graduate or undergraduate programs in analytics (e.g., masters of science in business analytics [MSBA] and masters of management analytics [MMA]) and/or in management (e.g., masters of science in management [MScM] and masters in management [MiM, MM]).

The teaching note for the case contains the pedagogy and the analyses, alongside the detailed explanations of the various techniques and their implementations in R (code provided in Exhibits and supplementary files). Python code, as well as the spreadsheet implementation in XLMiner, are available upon request.

Uber had pioneered the growth and delivery of modern ridesharing services by leveraging the explosive growth of technology, GPS navigation, and smartphones. Ridesharing services had expanded across the world, growing rapidly in the United States, China, India, Europe, and Southeast Asia. Even as these services expanded and gained popularity, however, the pickup experience for drivers and riders did not always meet the expectations of either party. Pickups were complicated by traffic congestion, faulty GPS signals, and crowded pickup venues. Flawed pickups resulted in rider dissatisfaction and in lost revenues for drivers. Uber had identified the pickup experience as a top strategic priority, and a team at Uber, led by group product manager Birju Shah, was tasked with designing an automated solution to improve the pickup experience. This involved three steps. First, the team needed to analyze the pickup experience for various rider personas to identify problems at different stages in the pickup process. Next, it needed to create a model for predicting the best rider location for a pickup. The team also needed to develop a quantitative metric that would determine the quality of the pickup experience. These models and metrics would be used as inputs for a machine learning.