A new method for fraud detection in credit cards based on transaction dynamics in subspaces

Abstract

[EN] This paper presents a new method for fraud detection in credit cards based on exploiting the dynamics of the card transactions. We hypothesize different behavior models in the use of the card between legitimate clients and fraudsters that are registered in the sequential pattern that follows the transactions. The method considers analyses in subspaces defined by two or three variables recorded in the transactions. From these subspaces, several dynamic features, such as transaction velocity and acceleration, are estimated as input vectors for a classification process. Linear and quadratic discriminant analysis and random forest are implemented as single classifiers. All the single classification results obtained for each of the subspaces are late fused to obtain an overall result using alpha integration algorithm. The proposed method was evaluated using a subset of real data with a very low fraud to legitimate transaction ratio. We demonstrated that the temporal dependence of card transactions exploited in different subspaces and fused to give an overall result improves the detection accuracy of fraud detection in credit cards.