A Machine Learning Approach for Detection of Fraud Based on SVM

The growth of e-commerce increases the money transaction via electronic network which is designed for hassle free fast & easy money transaction but the facility involves greater risk of misuse of facility for fraud one of them is credit card fraud it can be happened by many types as by stolen card, by internet hackers who can hack your system & get important information about your card, or by information leakage during the transaction, although many person has proposed their work for credit card fraud detection by characterizing the user spending profile, but in this paper we are proposing the SVM(support vector machine) based method with multiple kernel involvement also including several fields of user profile instead of only spending profile & the simulation result shows improvement in TP(true positive), TN(true negative) rate, it also decreases the FP(false positive) & FN(false negative) rate.