Probability Models for Customer-Base Analysis
November 17-18, 2011 A workshop offered at Wharton San Francisco
9:00 am - 4:00 pm For pricing info click the Logistics tab below Register here
Workshop Overview
Customer-base analysis seeks to use information on the history of customer purchase patterns to address forward-looking questions such as: (1) Which individuals are most likely to be active (or inactive) customers in a future period of time? (2) What will the aggregate and disaggregate purchase patterns look like for a group of customers in the future period? (3) What will be the “customer lifetime value” for a group of customers listed in the firm’s database? An increasingly large number of practitioners have been charged by senior management to obtain valid answers to these kinds of questions, but unfortunately their skills – and the set of commonly available commercial tools – are not well-suited for these important tasks.
This two-day workshop aims to fill in these gaps by bringing sophisticated practitioners fully up to speed on the essential techniques that should underlie their customer-base forecasting activities. Our two main objectives are: (1) to overview the basics of using probability models for forecasting purposes in general, and (2) to use these “building blocks” in a series of focused models/examples that illustrate several state-of-the-art approaches towards customer-base analysis.
*When registering, please indicate how you learned about this program, for example:
Wharton Customer Analytics Initiative (WCAI) newsletter, WCAI personal outreach, Wharton Executive Education, Wharton@Work, etc.
"Probability Models for Customer-Base Analysis" is subsidized and co-sponsored by the Wharton Customer Analytics Initiative and Wharton Executive Education.
Program Audience Faculty Logistics
On the first day, we develop participants' skills through a set of case studies that demonstrate the model-building process in detail. We illustrate and carefully discuss all of the steps required to develop different types of probability models for forecasting customer behavior. Extensive use is made of the Solver tool in Microsoft Excel, which makes it possible to construct all of these models within a familiar spreadsheet environment. By the end of the day, participants should be quite comfortable with the main principles of probability models (as applied to forecasting) and the managerial issues that surround them.
On the second day, we drill down more specifically into the domain of customer-base analysis. As before, we focus on developing the models primarily in Excel, and we provide attendees with the relevant spreadsheets and notes on how to implement the models from scratch. Our goal is to provide attendees with tools that can be applied immediately to their own customer-level data. We use the methods covered in the first day to construct the kinds of models needed to address the aforementioned questions associated with customer-base analysis.
By the end of the seminar, participants will understand the critical concepts and techniques required to make meaningful and accurate forecasts of customer behavior in a variety of different managerial settings. Likewise, they will be keenly aware of the limitations and concerns of other approaches that are often used for similar purposes. Thus, besides having the skills to build models themselves, participants will know how to ask the right questions of consultants and IT vendors who offer services in this important area.
