A Novel Prediction Model for Credit Card Risk Management

The amount of issued credit cards has increased rapidly in Taiwan and is characterized as high risk business if comparing to that of the traditional banking loan. To minimize the operating risks and maximize business profits, the credit card issuing institutions need an intelligent system to support the process of the risk management after cards issued. The aim of this study is to construct an efficient risk prediction system to detect the possible defaults for the credit card holders. The system collects the personal and financial information about the credit card holders and then applies evolutional neural network which integrated with grey incidence analysis and Dempster-Shafer theory of evidence to predict the default cases. The experimental results show the integrated model has better prediction accuracy if compare to the model which applies evolutional neural network only and is capable of tracing and reducing the default risks.