Prev
By
- Kinshuk Jerath, Carnegie Mellon University - David A. Tepper School of Business
- Peter Fader, University of Pennsylvania - Marketing Department
- Bruce Hardie, London Business School
Abstract: We address a critical question that many firms are facing today:
Can customer data be stored and analyzed in an easy-to-manage, scalable, privacy-preserving format without significantly compromising the inferences that can be made about the customers' purchasing activity?
A number of researchers have developed customer-base analysis models that perform very well given individual-customer-level data. We explore the possibility of estimating these models using repeated cross-sectional summaries (RCSS) of the transaction data (e.g., four quarterly histograms). Such summaries are easy to create, easy to distribute, and free of any privacy concerns. We focus on the widely used Pareto/NBD model and carry out a comprehensive simulation study covering a vast spectrum of market scenarios. Our results consistently and convincingly establish that the model fit (and parameter values) associated with the use of three or four cross-sections of RCSS data can closely match the model fit (and parameter values) associated with the use of individual-level data. We also confirm the results of the simulations on a real dataset of online CD purchases.
Keywords: Customer-Base Analysis, Privacy-Preserving, Scalability, Data Aggregation, Information Loss, Pareto/NBD
Free download at
papers.ssrn.com/sol3/papers.cfm?abstract_id=1708562