Predicting repayment of the credit card debt

The recent economic crisis not only reduces the profit of retailer stores but also incurs the significant losses caused by increasing the late-payment rate of credit cards. Under this pressure, the scope of credit prediction needs to be broadened to the customer management after delinquency occurs. In doing so, this study clusters the credit card debtors in a retail company into homogeneous segments by using a self-organizing map. This study then develops credit prediction models to recognize the repayment patterns of each segment by using a Cox proportional hazard analysis. The credit prediction models are evaluated and the managerial implications of the study are provided. (C) 2010 Elsevier Ltd. All rights reserved.