Credit Card Fraud Detection Based on DeepInsight and Deep Learning

Abstract

In this paper, we propose a credit card fraud detection method that leverages DeepInsight and deep learning. The proposed method employs the DeepInsight mechanism to convert non-image credit card transaction data into structured images. These images are then processed by a parallel convolutional neural network (CNN) deep learning model to extract crucial hidden features for credit card fraud detection. To evaluate the performance of our method, we utilize European credit card transaction data. The evaluation results are compared with those of related methods, demonstrating the superiority of our proposed method in terms of the accuracy, true positive rate, true negative rate, and Matthews correlation coefficient.