COMPARATIVE EVALUATION OF MACHINE LEARNING ALGORITHMS AND CLASS IMBALANCE HANDLING STRATEGIES FOR CREDIT CARD FRAUD DETECTION
DOI:
https://doi.org/10.5281/zenodo.23319034Abstract
Severe class imbalance complicates the evaluation of credit card fraud detection models. This study compares six classifiers under no balancing, class weighting, SMOTE, and random undersampling, yielding 24 configurations. Experiments used approximately 1.85 million synthetic Sparkov transactions with a temporal train-test split. Average Precision (AP) was the primary metric, complemented by classification and alert-budget measures.Keywords
credit card fraud detection, machine learning, class imbalance, SMOTE, XGBoost, Average Precision, SHAPReferences
1. Preciado Martínez P. M., Reier Forradellas R. F., Garay Gallastegui L. M., Náñez Alonso S. L. Comparative analysis of machine learning models for the detection of fraudulent banking transactions. (2025). Cogent Business & Management, 12(1). https://doi.org/10.1080/23311975.2025.2474209
2. Dichev, A., Zarkova, S., & Angelov, P. (2025). Machine Learning as a Tool for Assessment and Management of Fraud Risk in Banking Transactions. Journal of Risk and Financial Management, 18(3). https://doi.org/10.3390/jrfm18030130
3. Naqvi S., H. (2026). Fraud Detection Using Machine Learning in Financial Transactions: A Systematic Review. Veredas do Direito, 23. https://doi.org/10.18623/rvd.v23.n2.4187
4. Saito, T., & Rehmsmeier, M. (2015). The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets. PLoS ONE, 10(3). https://doi.org/10.1371/journal
5. Chawla N., V., Bowyer K., W., Hall L., O., & Kegelmeyer W., P. (2002). SMOTE: Synthetic Minority Over-sampling Technique. Journal of Artificial Intelligence Research, 16, 321–357. https://doi.org/10.1613/jair.953
6. Singh, A., & Jain, A. (2022). An efficient credit card fraud detection approach using cost-sensitive weak learner with imbalanced dataset. Computational Intelligence, 38(6), 2035–2055. https://doi.org/10.1111/coin.12555
7. Wijaya M., G., Pinaringgi M., F., & Zakiyyah A., Y. (2024). Meiliana. Comparative Analysis of Machine Learning Algorithms and Data Balancing Techniques for Credit Card Fraud Detection. Procedia Computer Science, 245, 677–688. https://doi.org/10.1016/j.procs.2024.10.294
8. Btoush, E., Kobbaey, T., Tamimi, H., & Zhou, X. (2026). Machine Learning-Based Cyber Fraud Detection: A Comparative Study of Resampling Methods for Imbalanced Credit Card Data. Applied Sciences, 16(2). https://doi.org/10.3390/app16020850
9. Singh, A., Ranjan R., K., & Tiwari, A. (2022). Credit Card Fraud Detection under Extreme Imbalanced Data: A Comparative Study of Data-level Algorithms. Journal of Experimental & Theoretical Artificial Intelligence, 34(4), 571–598. https://doi.org/10.1080/0952813X.2021.1907795
10. Zuberi, N., Rahman M., M., Rashid S., U., Ahsan M., N., Rahman M., S., & Mollah M. H., O. (2026). R. A robust machine learning framework for detecting temporal drift in financial fraud prevention. Scientific Reports, 16, 41598–026. https://doi.org/10.1038/s41598-026-58285-5
11. Breskuvienė, D., & Dzemyda, G. (2024). Enhancing credit card fraud detection: highly imbalanced data case. Journal of Big Data, 11, 40537–024. https://doi.org/10.1186/s40537-024-01059-5
12. Le Borgne Y.-A., Siblini W., Lebichot B., Bontempi G. Reproducible Machine Learning for Credit Card Fraud Detection: Practical Handbook. — Brussels: Université Libre de Bruxelles, 2022. — https://fraud-detection-handbook.github.io/ fraud-detection-handbook/.
13. Shenoy, K. (2020). Credit Card Transactions Fraud Detection Dataset. //www.kaggle.com/datasets/kartik2112/fraud-detection.
14. Chen, T., & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794. https://doi.org/10.1145/2939672.2939785
15. Lundberg S., M., & Lee, S. (2017). -I. A Unified Approach to Interpreting Model Predictions. Advances in Neural Information Processing Systems 30, 4765–4774.
16. Konsta, L., Dimitriou, D., Papathanasiou, A., & Liagkou, V. (2026). Detecting Cyber Fraud in Banking Transactions via Machine Learning Techniques: Implications for Financial Stability. FinTech, 5(1). https://doi.org/10.3390/fintech5010023
Downloads
Published
How to Cite
Issue
Section
