A Study on Credit Card Fraud Detection Model

• Main Authors: Yueh Chin Tseng, 曾月金
• Other Authors: Feng Hsu Wang
• Format: Others
• Language: zh-TW
• Published: 2003
• Online Access: http://ndltd.ncl.edu.tw/handle/62427476051743309532

碩士 === 銘傳大學 === 資訊管理學系碩士在職專班 === 91 === As issuing banks progressively strive for promoting the utilization rate of credit cards to expedite their markets, frauds with credit cards are also continually growing. The amount of issued cards has been beyond 60 millions and the amount of used cards beyond 34 millions in Taiwan in one year by 2003. It is possible that one person can own more than one card. When the market speed up, the fraud of cards are simultaneously rising. It is believed that the banks have encountered a huge money loss beyond 30 billions in this year. The cardholders also worry about the risk of card frauds. In this thesis, we are concerning about the feasibility of adopting data mining techniques to develop an effective fraud detection system for credit cards. Due to the constraint caused by the privacy and safety problem of real transaction data, in this study a simulation program is coded to generate artifact transactions for simulation testing. We propose an integrated approach for dealing with the fraud detection problem. A clustering method is first applied to build a classification model for potential fraud transactions. Those transactions fall into this fraud group will be claimed to be in the warning list for further validation. On the other hand, those transactions falls outside of the fraud group are sent to the second classification module that might be built through the decision tree model or neural networks. Through a set of simulation experiments, it is shown that this integrated fraud detection approach is possible to reduce the detection errors. It was worth to study further transaction fraud detection of module.