期刊名称：International Journal of Computer Science & Technology
印刷版ISSN：2229-4333
电子版ISSN：0976-8491
出版年度：2012
卷号：3
期号：2
页码：515-519
语种：English
出版社：Ayushmaan Technologies
摘要：With the growth in Information Technology and advancement in communication channels, fraud is spreading all over the world, results in enormous financial losses. Due to a rapid improvement in the Electronic Commerce, use of credit cards has been increasing in dramatic pace. Since credit card becomes the most popular and common mode of payment, credit card frauds are becoming increasingly epidemic in recent years. It caused an explosion in the credit card fraud as credit card usage is increasing day by day. With the increase of usage of credit card as the most popular mode of payment for both online as well as regular purchase, cases of fraud link with it are also rising drastically. In actual, fraudulent transactions has been scattered with the genuine transactions. As simple pattern matching techniques are not often sufficient to detect those frauds accurately and precisely. Implementation of efficient Fraud Detection Systems (FDS) has thereby become compulsory for all credit card issuing banks to minimize their losses. In this paper, we survey several novel approaches for Credit Card Fraud Detection (CCFD), which combines indications from current as well as past behavior of card holders. Receiver Operating Characteristic (ROC) analysis technology is also introduced which ensures the accuracy and effectiveness of fraud detection.
