Credit Card Fraud Detection with a Cascade Artificial Neural Network and Imperialist Competitive Algorithm

Abstract

Credit Card Fraud is one of the biggest threats to business establish-ments today. This paper presents a cascade artificial neural network for the recognition of credit card fraud detection. This system aims at attaining a very high recognition rate and a very high reliability, In other words, excellent recognition performance of credit card fraud detection was obtained. Then, One solution was proposed: utilizing a cascade artificial neural networks for enhancing recog-nition rate and reducing rejection rate. The gating networks (GNs) are used to congregate the confidence values of three parallel ar-tificial neural networks (ANNs) classifiers. The Imperialist Com-petitive Algorithm (ICA) is a new evolutionary algorithm which was recently introduced and has a good performance in some opti-mization problems. The weights of the GNs are trained by the Im-perialist Competitive Algorithm (ICA) to achieve the overall opti-mal performance. The experiments conducted on the database from a large Brazilian bank produced encouraging results: high accu-racy of 98.56% with minimal rejection in the last cascade layer.