Search results

In the early months of the 2007-08 financial crises, a loan manager faces a real estate financing decision. Should he approve a bullet structure three-year loan to a longstanding client, a legendary Texan developer? The developer, who near retirement downsized his business, is seeking financing for his only project: residential or commercial development on an attractive piece of land in suburban Houston. The loan manager considers the decision in light of the mortgage market turmoil, seeing commercial projects as safer, but also factoring that the residential market could bring higher returns if the market stabilizes soon. The manager collects the data and asks an analyst to assess the risks; that ultimately requires assessing the economics of both projects from both the bank's and the developer's perspectives. The bank could still change the interest rate on the loan to receive adequate compensation for the risk it carries, but the loan manager knows that doing so will change their long-term client willingness to take on the loan.

In the first case of a two-part series, a strategic finance manager at Wells Fargo with experience installing solar panel systems on bank branches crunches the numbers for a similar project in the Los Angeles area given the uncertain future of a government rebate.

“A Canadian online floral delivery company considers whether to source more flowers from its existing growing locations and which of those would be optimal given its current market. What would be the advantages of opening a logistics facility in Miami? Students must consider the transportation costs per standard box from each origin or transshipment center to each production facility as well as data about the available supply at each origin and projected demand at each facility per week.”

This case exposes students to predictive analytics as applied to discrete events with logistic regression. The VP of customer services for a successful start-up wants to proactively identify customers most likely to cancel services or “churn.” He assigns the task to one of his associates and provides him with data on customer behavior and his intuition about what drives churn. The associate must generate a list of the customers most likely to churn and the top three reasons for that likelihood.

This case is suitable for graduate-level quantitative analysis, business and government, environment and sustainability, and global economics courses. Students must consider the tradeoffs between continuing to run an old coal-burning plant and purchasing emissions allowances (EAs) versus upgrading to emissions-reducing wet or dry scrubbers. Reducing emissions creates the possibility of selling the plant's surplus EAs (which are likely to increase in price). Choosing a wet or dry scrubber requires considering installation cost and construction time, variable cost, and SO2 removal efficiency. Ideally, the investment should pay back over time, but management believes some net investment could also be justified. For that, however, complete analyses from both economic and environmental perspectives are required. A supplemental spreadsheet is available to accompany the case (UVA-QA-0726X).

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.