Fraud Detection in Financial Transactions Using Ensemble Machine Learning Models

Financial fraud has been identified as a critical challenge in the banking and e-commerce sectors, necessitating the need for accurate and efficient detection systems. Therefore, this study proposes the adoption of an XGBoost-based machine learning model for credit card fraud detection by leveraging on publicly available transactional datasets. Preprocessing steps, including normalization of numerical features and Principal Component Analysis (PCA) on anonymized components were further applied in order to enhance model learning and reduce dimensionality, while class imbalance was addressed using scale_pos_weight and the model was trained and evaluated using stratified train-test splits and hyperparameter optimization, with performance of the model assessed through accuracy, precision, recall, F1-score, and ROC-AUC. Experimental results in the study demonstrated that the proposed system achieves high predictive performance, with a validation accuracy of 94.9%, precision of 92.8%, recall of 90.5%, and ROC-AUC of 94.7%, thereby effectively detecting fraudulent transactions while minimizing false positives. Finally, comparative analysis was conducted and it indicated that the model performs competitively against existing methods, highlighting the importance of robust preprocessing and feature engineering. The proposed system is modular and scalable, offering practical applicability for real-time financial fraud detection, thereby enhancing transaction security and reliability.

Financial Fraud Detection; XGBoost; Machine Learning; Imbalanced Data

1. Al Ali, A., Alazab, M., & Khan, S. (2023). A hybrid deep learning model for financial fraud detection using blockchain and ensemble methods. Computers, 12(3), 78. https://doi.org/10.3390/computers12030078 [Google Scholar] [Crossref]

2. Alazab, M., Tang, M., & Alazab, M. (2021). Deep learning for cybersecurity and fraud detection in financial transactions. Electronics, 10(5), 593. https://doi.org/10.3390/electronics10050593 [Google Scholar] [Crossref]

3. Asnawi, M. F., & Zacky, M. (2025). The application of XGBoost classification for credit card fraud detection using SMOTE. Journal of Computer Science and Engineering Technology, 15(2), 92–104. https://journal.nacreva.com/index.php/cest/article/view/131 [Google Scholar] [Crossref]

4. Deng, Y., Zhang, H., & Li, X. (2025). Ensemble learning for fraud detection in imbalanced financial datasets. Journal of Intelligent & Fuzzy Systems, 39(1), 115–126. https://doi.org/10.3233/JIFS-230456 [Google Scholar] [Crossref]

5. Kabane, S. (2024). Impact of sampling techniques and data leakage on XGBoost performance in credit card fraud detection. arXiv Preprint, arXiv:2412.07437. https://arxiv.org/abs/2412.07437 [Google Scholar] [Crossref]

6. Kumar, A., Sharma, R., & Singh, P. (2023). Explainable AI for financial fraud detection using XGBoost and SHAP. Journal of Intelligent Systems, 32(1), 45–58. https://doi.org/10.1515/jisys-2022-0034 [Google Scholar] [Crossref]

7. Kumar, R., & Singh, A. (2022). Credit card fraud detection using XGBoost and ensemble learning. International Journal of Information Technology, 14(3), 567–574. https://doi.org/10.1007/s41870-021-00791-4 [Google Scholar] [Crossref]

8. Niu, X., Wang, L., & Yang, X. (2019). A comparison study of credit card fraud detection: Supervised versus unsupervised. arXiv Preprint, arXiv:1904.10604. https://arxiv.org/abs/1904.10604 [Google Scholar] [Crossref]

9. Nwakeze, O. M. (2024). The role of network monitoring and analysis in ensuring optimal network performance. International Research Journal of Modernization in Engineering Technology and Science. https://doi.org/10.56726/irjmets59269 [Google Scholar] [Crossref]

10. Oboti, N. P., Nwakeze, O. M., & Mohammed, N. U. (2025). Enhancing risk management with human factors in cybersecurity using behavioural analysis and machine learning technique. European Journal of Computer Science and Information Technology, 51(13), 101–118. [Google Scholar] [Crossref]

11. Purwar, A., & Manju. (2023). Credit card fraud detection using XGBoost for imbalanced datasets. In Proceedings of the 2023 Fifteenth International Conference on Contemporary Computing (IC3) (pp. 1–6). https://dl.acm.org/doi/10.1145/3607947.3607986 [Google Scholar] [Crossref]

12. Rahmadani, A., Zacky, M., & Michael, J. P. (2025). Classification of a credit card fraud detection model using XGBoost with SMOTE and GridSearchCV optimization. International Journal of Advanced Computer Science and Applications, 16(1), 45–53. https://journal.irpi.or.id/index.php/ijatis/article/view/2273 [Google Scholar] [Crossref]

13. Vinod Shankar, P., Padma, A., & Ravi, V. (2025). A comprehensive review of lightweight blockchain practices for smart cities: A security and efficacy assessment. Journal of Reliable Intelligent Environments, 11(13). https://doi.org/10.1007/s40860-025-00254-2 [Google Scholar] [Crossref]

14. Zhang, Y. (2020). Handling class imbalance in fraud detection using cost-sensitive learning. Expert Systems with Applications, 161, 113715. https://doi.org/10.1016/j.eswa.2020.113715 [Google Scholar] [Crossref]

15. Zhou, Y., Li, J., & Wang, H. (2023). Ensemble learning for financial fraud detection: A comparative study. Computers & Security, 125, 102973. https://doi.org/10.1016/j.cose.2022.102973 [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet