Intelligent fraudulent detection system based SVM and optimized by danger theory

Since past few years there is tremendous advancement in electronic commerce technology, and the use of credit cards has increased dramatically. As credit card becomes the most popular mode of payment for both online as well as regular purchase, cases of fraud associated with it are also rising. In this paper the authors present the underlying theory of a hybrid model of an Intelligent Fraudulent Detection System to detect fraud in credit card transaction processing by the fusion of Danger theory and Support Vector Machine (SVM). In this Intelligent Fraudulent Detection System, the SVM is initially trained with the normal behavior of a cardholder. If an incoming credit card transaction is not accepted by the trained SVM with sufficiently high probability, it is considered to be fraudulent. At the same time, the detection system tries that the genuine transactions are not rejected by making it more immune by the fusion of danger theory mechanism.