A Novel Fraud Detection Scheme for Credit Card Usage Employing Random Forest Algorithm Combined with Feedback Mechanism

As electronic commerce has gained wide spread popularity payments made for the transactions performed by users through credit card also gained an equal amount of reputation. Whenever shopping through web is made the chance for the occurrence of fraudulent activities are escalating. In this paper we have proposed a three phase scheme to detect the fraudulent activities. A profile for the card users based on their behavior is created by employing machine learning technique. In the second phase extraction of group of precise communicative pattern for the card users depending upon the accumulated transactions and the users earlier transactions. A collection of classifiers are then trained based on all behavioral pattern. The trained collection of classifiers are then used to detect the online fraudulent activities occurred and if an emerging transaction is found to be fraudulent, a feedback is taken which resolves the quandary caused by the drift in the notion. Experiments performed indicated that the proposed scheme works better than other schemes.