An Analysis of Machine Learning Models Applied in Credit Card Fraud Detection

Saha, Anup Kumar

Abstract

Credit cards are a type of modern financial asset that is convenient, secure, and beloved by consumers. However, a huge amount of fraud in financial transactions is occurring on a daily basis, so it is important to have effective fraud detection systems to protect digital payment. Traditional rule based systems for fraud detection are however not very effective in dynamic environments as they cannot detect new patterns and methods used by fraudsters. Addressing this, this study explores four machine learning models, including Graph Neural Networks (GNN), Long Short Term Memory (LSTM), Multilayer Perceptron (MLP), and Transformer to detect credit card fraud in an imbalanced dataset. For use of the synthetic minority over-sampling technique (SMOTE) in the imbalanced dataset, the machine learning models demonstrate a great improvement in classification accuracy. The results reveals the effectiveness of each model, with GNNs and LSTMs being the best in managing the complexities of transaction data.

Citation

Al Arafat, K. A., Saha, A. K., Hossain, M. I., Shepard, B., Richards, J., & Parvez, I. (2025, May). An Analysis of Machine Learning Models Applied in Credit Card Fraud Detection. Presented at IEEE International Conference on Electro Information Technology, Valparaiso, Indiana, USA

• Presentation Conference Type: Conference Paper (published)
• Conference Name: IEEE International Conference on Electro Information Technology
• Start Date: May 29, 2025
• End Date: May 31, 2025
• Acceptance Date: Apr 22, 2025
• Online Publication Date: Aug 12, 2025
• Publication Date: Aug 12, 2025
• Deposit Date: Apr 24, 2025
• Journal: IEEE International Conference on Electro-Information Technology
• Print ISSN: 2154-0357
• Electronic ISSN: 2154-0373
• Publisher: Institute of Electrical and Electronics Engineers (IEEE)
• Peer Reviewed: Peer Reviewed
• Pages: 151-155
• Book Title: 2025 IEEE International Conference on Electro Information Technology (eIT)
• ISBN: 979-8-3315-3234-5
• DOI: https://doi.org/10.1109/eIT64391.2025.11103615
• Public URL: https://keele-repository.worktribe.com/output/1199675
• Publisher URL: https://ieeexplore.ieee.org/document/11103615
• Related Public URLs: https://www.eit-conference.org/