Fraud Detection in Credit Card System Using Web Mining

Now a day the usage of credit cards has dramatically increased. 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. Various techniques like classification, clustering and apriori of web mining will be integrated to represent the sequence of operations in credit card transaction processing and show how it can be used for the detection of frauds. Initially, web mining techniques trained with the normal behaviour of a cardholder. If an incoming credit card transaction is not accepted by the web mining model with sufficiently high probability, it is considered to be fraudulent. At the same time, the system will try to ensure that genuine transactions will not be rejected. Using data from a credit card issuer, a web mining model based fraud detection system will be trained on a large sample of labelled credit card account transactions and tested on a holdout data set that consisted of all account activity. Web mining techniques can be trained on examples of fraud due to lost cards, stolen cards, application fraud, counterfeit fraud, and mail-order fraud. The proposed system will be able to detect frauds by considering a cardholder‟s spending habit without its significance. Usually, the details of items purchased in individual transactions are not known to any Fraud Detection System. The proposed system will be an ideal choice for addressing this problem of current fraud detection system. Another important advantage of proposed system will be a drastic reduction in the number of False Positives transactions. FDS module of proposed system will receive the card details and the value of purchase to verify, whether the transaction is genuine or not. If the Fraud Detection System module will confirm the transaction to be of fraud, it will raise an alarm, and the transaction will be declined.