A Hybrid Approach based on Ensemble Learning and SMOTE Technique for Credit Card Fraud Detection

In this study, a model for detecting credit card fraud is developed using the ensemble learning approach to identify legitimate and fraudulent transactions. The dataset was collected from the open-source Kaggle repository. The min-max and SMOTE techniques were applied to the dataset to prepare it for ML algorithms. The pre-processed dataset was given to five ML algorithms, including LR, DT, RF, KNN, and XGBoost, and evaluated using various performance metrics. The key finding from this evaluation shows that RF, KNN, and XGBoost outperform LR and DT algorithms. The outperforming ML algorithms were chosen for hyper-parameter tuning using the Optuna optimizer. After hyper-tuning, the best two ML algorithms were selected in the ensemble learning, and their predictions were combined using the weighted voting classifier. We have assigned the 0.7 weight value to the best ML algorithm, whereas the second-best ML algorithm was given a 0.3 weight value. The simulation results show that the proposed method achieves an accuracy value of 0.99696, a precision value of 0.903226, a recall value of 0.879581, an F1-score value of 0.879581, an ROC-AUC value of 0.975524, and a PR-AUC value of 0.882359. The comparative analysis shows that the proposed method outperforms the existing approaches developed by Alarfaj et al. [3] and Karunya et al. [11]. In the future, we will explore other data balancing and optimization approaches for balance the data classes and hyper-tune the parameters of the ML algorithms.

[1] N. Baisholan, J. E. Dietz, S. Gnatyuk, M. Turdalyuly, E. T. Matson, and K. Baisholanova, “A Systematic Review of Machine Learning in Credit card fraud detection under original class imbalance,” Computers, vol. 14, no. 10, p. 437, Oct. 2025, doi: 10.3390/computers14100437. Available: https://doi.org/10.3390/computers14100437 [2] R. B. Sulaiman, V. Schetinin, and P. Sant, “Review of Machine Learning Approach on Credit Card Fraud Detection,” Human-Centric Intelligent Systems, vol. 2, no. 1–2, pp. 55–68, May 2022, doi: 10.1007/s44230-022-00004-0. Available: https://doi.org/10.1007/s44230-022-00004-0 [3] F. K. Alarfaj, I. Malik, H. U. Khan, N. Almusallam, M. Ramzan, and M. Ahmed, “Credit card fraud detection using state-of-the-art machine learning and deep learning algorithms,” IEEE Access, vol. 10, pp. 45498–45510, 2022, doi: 10.1109/ACCESS.2022.3166891. [4] E. Ileberi, Y. Sun, and Z. Wang, “Performance evaluation of machine learning methods for credit card fraud detection using SMOTE and AdaBoost,” IEEE Access, vol. 9, pp. 165286–165294, Jan. 2021, doi: 10.1109/access.2021.3134330. Available: https://doi.org/10.1109/access.2021.3134330 [5] A. R. Khalid, N. Owoh, O. Uthmani, M. Ashawa, J. Osamor, and J. Adejoh, “Enhancing Credit Card Fraud Detection: An ensemble Machine learning approach,” Big Data and Cognitive Computing, vol. 8, no. 1, p. 6, Jan. 2024, doi: 10.3390/bdcc8010006. Available: https://doi.org/10.3390/bdcc8010006 [6] H. S. Alsagri, “Hybrid Machine Learning-Based Multi-Stage framework for detection of credit card anomalies and fraud,” IEEE Access, vol. 13, pp. 77039–77048, Jan. 2025, doi: 10.1109/access.2025.3565612. Available: https://doi.org/10.1109/access.2025.3565612 [7] N. Baisholan, J. E. Dietz, S. Gnatyuk, M. Turdalyuly, E. T. Matson, and K. Baisholanova, “FraUdX AI: An interpretable machine learning framework for credit card fraud detection on imbalanced datasets,” Computers, vol. 14, no. 4, p. 120, Mar. 2025, doi: 10.3390/computers14040120. Available: https://doi.org/10.3390/computers14040120 [8] R. K. Gupta et al., “Enhanced framework for credit card fraud detection using robust feature selection and a stacking ensemble model approach,” Results in Engineering, vol. 26, p. 105084, Apr. 2025, doi: 10.1016/j.rineng.2025.105084. Available: https://doi.org/10.1016/j.rineng.2025.105084 [9] L. Theodorakopoulos, A. Theodoropoulou, A. Tsimakis, and C. Halkiopoulos, “Big Data-Driven distributed machine learning for scalable credit card fraud detection using PySpark, XGBoost, and CatBoost,” Electronics, vol. 14, no. 9, p. 1754, Apr. 2025, doi: 10.3390/electronics14091754. Available: https://doi.org/10.3390/electronics14091754 [10] M. Zavvar et al., “A hybrid deep learning framework using synthetic oversampling, autoencoder, convolutional neural networks, and an attention mechanism for credit card fraud detection,” Journal of Big Data, vol. 13, no. 1, Dec. 2025, doi: 10.1186/s40537-025-01331-2. Available: https://doi.org/10.1186/s40537-025-01331-2