Discovering heterogeneous consumer groups from sales transaction data |
| |
| Institution: | 1. School of Business, Pusan National University, Busan, Republic of Korea;2. Department of Information and Communication Engineering, DGIST, Daegu, Republic of Korea;1. Carey Business School, Johns Hopkins University, 100 International Drive, Baltimore, MD 21202, United States;2. Department of Information Systems and Business Analytics, Florida International University, Miami, FL 33199, United States;1. College of Auditing and Evaluation, Nanjing Audit University, Nanjing, Jiangsu Province, 211815, China;2. Schulich School of Business, York University, Toronto, Ontario M3J 1P3, Canada;3. Foisie Business School, Worcester Polytechnic Institute, Worcester, MA 01609, USA;1. School of Business, Stevens Institute of Technology, 1 Castle Point Terrace, Hoboken, NJ 07030, USA;2. Lally School of Management, Rensselaer Polytechnic Institute, 110 8th Street, Pittsburgh Building, Troy, NY 12180, USA;3. Division of Economic and Risk Analysis, US Securities and Exchange Commission, 100 F St NE, Washington DC 20549, USA;4. Department of Electrical, Computer & Systems Engineering, Rensselaer Polytechnic Institute, Jonsson Engineering Center 6048, Troy, NY 12180, USA;1. Department of Industrial Engineering, University of Houston, 4800 Calhoun Road, Houston, TX 77204, USA;2. PROS Revenue Management, Houston, TX 77002, USA;3. Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA;1. Leiden University Mathematical Institute, Niels Bohrweg 1, 2333 CA, Leiden, NL, UK;2. Department of Management Science, Center for Transportation and Logistics, Lancaster University Management School, Bailrigg, Lancaster LA1 4YX, UK |
| |
| Abstract: | We propose a demand estimation method to discover heterogeneous consumer groups. The estimation requires only historical sales data and product availability. Consumers belonging to different segments possess heterogeneous preferences and, in turn, heterogeneous substitution behaviors. For such consumers, the latent class consumer choice model can better represent their heterogeneous purchasing behaviors. In the latent class choice model, there are multiple consumer segments, and the segment types are not observable to the retailer. The expectation-maximization (EM) method is developed to jointly estimate the arrival rate and the parameters of the choice model. The developed method enables a simple estimation procedure by treating the observed data as incomplete observations of the consumer type along with consumer’s first choice. The first choice is the choice before the substitution effects occur. We test the procedure on simulated data sets. The results show that the procedure effectively detects heterogeneous consumer segments that have significant market presence. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
