Abstract—With the increasing use of credit cards in electronic payments, financial institutions and service providers are vulnerable to fraud, costing huge losses every year. The design and the implementation of efficient fraud detection system is essential to reduce such losses. However, machine learning techniques used to detect automatically card fraud do not consider fraud sequences or behavior changes which may lead to false alarms. In this paper, we develop a credit card fraud detection system that employs Long Short-Term Memory (LSTM) networks as a sequence learner to include transaction sequences. The proposed approach aims to capture the historic purchase behavior of credit card holders with the goal of improving fraud detection accuracy on new incoming transactions. Experiments show that our proposed model gives strong results and its accuracy is quite high.
 

Index Terms—credit card, fraud detection, sequence learning, recurrent neural networks, LSTM

Cite: Ibtissam Benchaji, Samira Douzi, and Bouabid El Ouahidi, "Credit Card Fraud Detection Model Based on LSTM Recurrent Neural Networks," Journal of Advances in Information Technology, Vol. 12, No. 2, pp. 113-118, May 2021. doi: 10.12720/jait.12.2.113-118

Copyright © 2021 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.