Search results

The decision maker is in charge of procurement auctions at the department of transportation of Orangia (a fictitious U.S. state). Students are asked to assist him in estimating the winning bids in various auctions concerning highway repair jobs using data on past auctions. The decision maker is faced with various professional, statistical, and ethical dilemmas.

To analyze highway procurement auctions from the buyer-auctioneer perspective, establish basic facts regarding the project price-to-estimated cost ratio, set up and estimate a structural regression model to predict the winning bid, and compute the probability the winning price will be below estimated cost. Difficulties include heteroskedasticity, logarithmic specification, and omitted variable bias. Also to estimate a Logit regression and predict bidder collusion probability.

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.

Supplements the (A) case.

Robert Davidson, pricing manager for Tupelo Medical, was concerned about the variability in price paid for its top-selling product, the Micron 8 Series blood pressure monitoring system. Using historical transaction data, Davidson must determine the appropriate price floor. Setting a price too high risked the loss of a large number of customers, putting the company at substantial risk due to the importance of the product. Setting a price too low would impact Davidson's ability to meet the stated objective of increasing margins by 3 percent. He wondered what the optimal price floor would be and what the expected profits would be for that new price floor. Additionally, the company's business varied considerably by geographic region, account size and account type. As a result, he needed to consider whether it made sense to set a single price floor or whether he could improve profits by allowing some variability in the price floor by customer segment.

• To illustrate how one can build a data-driven pricing model to study the tradeoff between margin and probability of winning a sale in a B2B market

• To quantify the value from implementing a price floor with a B2B sales force

• To demonstrate the incremental value of implementing a price floor that varies by customer segment.

To illustrate how one can build a data-driven pricing model to study the tradeoff between margin and probability of winning a sale in a B2B market

To quantify the value from implementing a price floor with a B2B sales force

To demonstrate the incremental value of implementing a price floor that varies by customer segment.

Tom Feldman took a buyout from a large technology company and used part of the money to enroll in the MBA program of a reputed university in the metropolitan Houston, Texas area. While in the MBA program, Tom began evaluating potential businesses with the objective of identifying one that would suit his needs. As part of an MBA course in marketing, Tom put together a student team to conduct marketing research on an opportunity to open a party center in Houston. After his team completed the study, Tom had both financial and marketing data to make a decision about the launch.

Teaching case based on the primary research.

This case is suited for a marketing course at both the undergraduate and graduate levels.

Narayana, the head of Market Dynamic's (MD) Telecom vertical was working on the data analysis plan for the research on the telecom project that they had done for CWP. CWP was a well known consultant and had conducted a research with MD to generate consumer insights in the telecom space. These would help bring credibility for CWP and help in business development. CWP had requested for an early delivery and Narayana was planning to work on the analysis plan himself as his chief analyst was on leave. This case highlights the importance of an analysis plan in research. Specifically, it illustrate the role of different tools in data analysis and familiarizes participants with various tools and their applications. This case would be useful for students in Business Research and Market Research courses.