In e-commerce, credit card fraud is an evolving problem. The growing number of credit card transactions provides more opportunity for thieves to steal credit card numbers and subsequently commit fraud. Credit card fraud can be perpetrated through stolen cards, counterfeit card and stolen card details. The defensive measure issuing bank can take to overcome this liability is by introducing fraud detection systems (FDSs) in their database. Although different methods have been implemented to detect fraud but application of probability and selection of threshold value add an extra advantage for FDS to detect anomalies in on-line transactions. Therefore this paper implements another method of selecting threshold values (dynamic/adaptive) based on individual cardholder spending profile. In order to increase the confidence of the threshold values the results are verified using performance metrics. The two methods were compared and the results showed that adaptive method is suitable for detecting fraud in credit card transactions.
展开▼