CIRJE-J-121 『CRM のデータ分析に理論とモデルを組み込む 消費者行動理論にもとづいたRF 分析』
"Incorporating Theory and Modeling in Data Analysis for CRM: RF Analysis based on a Consumer Behavior Model"
Author Name   阿部誠(Makoto Abe)
Date December 2004
Full Paper PDF file (only Japanese version available)
Remarks 『流通情報』, 2004年12月, No. 426 所収。  
Abstract (Japanese) Abstract (English)


While RFM analysis is popular among practioners, ad-hoc rules are often employed to judge whether customers are alive or not. Because customers do not declare explicitly when they are dead, a company infers a customer is dead if she did not make any purchase, for example, for over three months. Even with the same period of nonpurchase, however, customers with a long interpurchase time need not be worried for death whereas those with a short interpurchase time could be dead. Hence, it is very important to account for customer heterogeneity when assessing the survival of customers. In this research, using standard RF data, I will derive the survival probability of an individual customer based on the common hypotheses on consumer behavior.