Peer-Reviewed | Open Access | International Research Journal
Explainable Credit Card Fraud Detection: Comparative Evaluation of Machine Learning Models Using SHAP and LIME
Main Article Content
Abstract
Credit card fraud detection remains a critical challenge in financial security, with the extreme class imbalance inherent in transaction data posing significant obstacles to model development and evaluation. While machine learning models have demonstrated strong predictive capabilities, their “black-box” nature limits stakeholder trust and regulatory compliance. This study presents a comprehensive, statistically rigorous framework for explainable credit card fraud detection that addresses key limitations of prior work. Five machine learning classifiers—Logistic Regression, Decision Tree, Random Forest, XGBoost, and LightGBM—are systematically evaluated using predefined hyperparameter configurations informed by established best practices, multiple class imbalance handling strategies (class weighting, SMOTE, Borderline-SMOTE, and ADASYN), and 10-fold stratified cross-validation with statistical significance testing and Cohen’s d effect size analysis. Model performance is assessed using an extended suite of metrics, including Precision, Recall, F1-score, ROC-AUC, Average Precision, Matthews Correlation Coefficient, Sensitivity, and Specificity. Final test set results are reported with 95% bootstrap confidence intervals. The explainability analysis employs both SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations), providing global and local interpretability across available prediction categories. Experimental results on the European cardholder credit card dataset show that ensemble-based models—LightGBM (F1 = 0.7489, MCC = 0.7555), Random Forest (F1 = 0.7411, MCC = 0.7464), and XGBoost (F1 = 0.7328, MCC = 0.7412)—substantially outperform simpler classifiers after SMOTE resampling. The SHAP analysis identifies V14, V4, and V12 as the most influential features for fraud prediction. The study provides a reproducible, end-to-end framework with documented random seeds, software versions, and implementation details to facilitate replication and extension.
Article Details
Section
Articles
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
Explainable Credit Card Fraud Detection: Comparative Evaluation of Machine Learning Models Using SHAP and LIME. (2026). International Journal of Engineering, Science and Environment (IJESE), 1(1). https://ijese.in/journal/article/view/45
References
[1] W. Hilal, S. A. Gadsden, and J. Yawney, “Financial fraud: A review of anomaly detection techniques and recent advances,” Expert Systems with Applications, vol. 193, p. 116429, 2022.
[2] A. Abdallah, M. A. Maarof, and A. Zainal, “Fraud detection system: A survey,” Journal of Network and Computer Applications, vol. 68, pp. 90–113, 2016.
[3] A. Dal Pozzolo, O. Caelen, Y. A. Le Borgne, S. Waterschoot, and
G. Bontempi, “Learned lessons in credit card fraud detection from a practitioner perspective,” Expert Systems with Applications, vol. 41, no. 10, pp. 4915–4928, 2014.
[4] R. Guidotti, A. Monreale, S. Ruggieri, F. Turini, F. Giannotti, and
A. Pedreschi, “A survey of methods for explaining black box models,” ACM Computing Surveys, vol. 51, no. 5, pp. 1–42, 2019.
[5] A. B. Arrieta, N. Diaz-Rodriguez, J. Del Ser et al., “Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI,” Information Fusion, vol. 58, pp. 82–115, 2020.
[6] D. Minh, H. X. Wang, Y. F. Li, and T. N. Nguyen, “Explainable artificial intelligence: A comprehensive review,” Artificial Intelligence Review, vol. 55, pp. 3503–3568, 2022.
[7] L. Longo, M. Brcic, F. Cabitza et al., “Explainable artificial intelligence (XAI) 2.0: A manifesto of open challenges and interdisciplinary research directions,” Information Fusion, vol. 106, p. 102301, 2024.
[8] S. M. Lundberg and S. I. Lee, “A unified approach to interpreting model predictions,” in Advances in Neural Information Processing Systems (NeurIPS), vol. 30, 2017.
[9] M. T. Ribeiro, S. Singh, and C. Guestrin, ““Why Should I Trust You?”: Explaining the predictions of any classifier,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2016, pp. 1135–1144.
[10] S. Kumar, S. Ahmad, and M. Uddin, “Explainable machine learning for credit card fraud detection: Balancing accuracy and interpretability,” Journal of Computational Science, vol. 75, p. 102200, 2024.
[11] M. Ali, S. Khan, and R. Patel, “A comprehensive framework for explain-able credit card fraud detection using SHAP and LIME,” Computers and Security, vol. 148, p. 103720, 2025.
[12] N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “SMOTE: Synthetic minority over-sampling technique,” Journal of Artificial Intelligence Research, vol. 16, pp. 321–357, 2002.
[13] H. He, Y. Bai, E. A. Garcia, and S. Li, “ADASYN: Adaptive synthetic sampling approach for imbalanced learning,” in IEEE International Joint Conference on Neural Networks. IEEE, 2008, pp. 1322–1328.
[14] A. Fernandez, S. Garcia, F. Herrera, and N. V. Chawla, “SMOTE for learning from imbalanced data: Progress and challenges, marking the 15-year anniversary,” Journal of Artificial Intelligence Research, vol. 61, pp. 863–905, 2018.
[15] 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. 39 700–39 715, 2022.
[16] A. A. Taha and S. J. Malebary, “An intelligent approach to credit card fraud detection using an optimized light gradient boosting machine,” IEEE Access, vol. 11, pp. 23 888–23 902, 2023.
[17] X. Zhang, Y. Han, W. Xu, and Q. Wang, “Credit card fraud detection using attention-based LSTM and gradient boosting models,” Expert Systems with Applications, vol. 224, p. 119913, 2023.
[18] Z. Wang, H. Liu, and Y. Chen, “Hybrid oversampling and explainable machine learning for financial fraud detection,” Information Sciences, vol. 665, p. 120381, 2025.
[19] N. Rtayli and N. Enneya, “Enhanced credit card fraud detection based on SVM-Recursive Feature Elimination and hyper-parameters optimiza-tion,” Journal of Information Security and Applications, vol. 55, p. 102596, 2020.
[20] S. M. Lundberg, G. Erion, H. Chen et al., “From local explanations to global understanding with explainable AI for trees,” Nature Machine Intelligence, vol. 2, no. 1, pp. 56–67, 2020.
[21] W. Chen, X. Li, and Y. Zhang, “SHAP-enhanced gradient boosting for interpretable fraud detection in financial transactions,” Knowledge-Based Systems, vol. 290, p. 111525, 2024.
[22] A. Singh and A. Jain, “Adaptive ensemble methods with explainable AI for financial fraud detection,” Applied Intelligence, vol. 54, no. 2, pp. 1580–1598, 2024.
[23] J. Forough and S. Momtazi, “Ensemble of deep sequential models for credit card fraud detection,” Applied Soft Computing, vol. 99, p. 106883, 2022.
[24] Z. Li, M. Huang, G. Liu, and C. Jiang, “A hybrid deep learning model for credit card fraud detection with feature engineering,” IEEE Transactions on Computational Social Systems, vol. 10, no. 4, pp. 1956–1967, 2023.
[25] A. Rahman, M. Islam, and N. Kumar, “Deep learning approaches for real-time credit card fraud detection: A comparative study,” Neural Computing and Applications, vol. 36, pp. 4521–4539, 2024.
[26] Y. Liu, X. Ao, Z. Qin, J. Chi, J. Feng, H. Yang, and Q. He, “Pick and choose: A GNN-based imbalanced learning approach for fraud detection,” in Proceedings of the Web Conference 2021. ACM, 2021,
pp. 3168–3177.
[27] D. Cheng, X. Wang, Y. Zhang, and L. Zhang, “Graph neural network for fraud detection via spatial-temporal attention,” IEEE Transactions on Knowledge and Data Engineering, vol. 34, no. 8, pp. 3800–3813, 2023.
[28] Y. Dou, Z. Liu, L. Sun, Y. Deng, H. Peng, and P. S. Yu, “Enhancing graph neural network-based fraud detectors against camouflaged fraud-sters,” Information Sciences, vol. 658, p. 119584, 2024.
[29] D. Ibomoiye and S. O. Akinola, “Attention-based transformer model for credit card fraud detection,” International Journal of Advanced Computer Science and Applications, vol. 14, no. 5, pp. 321–330, 2023.
[30] C. Yang, J. Zhang, and F. Wang, “Transformer-based anomaly detection for credit card fraud with self-attention mechanism,” Pattern Recogni-tion, vol. 148, p. 110167, 2024.
[31] M. Zhou, K. Li, and S. Wu, “Multi-head attention transformer networks for financial transaction fraud detection,” Expert Systems with Applica-tions, vol. 252, p. 124122, 2025.
[32] H. Han, W. Y. Wang, and B. H. Mao, “Borderline-SMOTE: A new over-sampling method in imbalanced data sets learning,” in International Conference on Intelligent Computing. Springer, 2005, pp. 878–887.
[33] L. Breiman, “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.
[34] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2016, pp. 785–794.
[35] G. Ke, Q. Meng, T. Finley, T. Wang, W. Chen, W. Ma, Q. Ye, and T. Y. Liu, “LightGBM: A highly efficient gradient boosting decision tree,” in Advances in Neural Information Processing Systems (NeurIPS), vol. 30, 2017.
[36] D. Chicco and G. Jurman, “The advantages of the matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation,” BMC Genomics, vol. 21, no. 1, p. 6, 2020.
[37] B. W. Matthews, “Comparison of the predicted and observed secondary structure of T4 phage lysozyme,” Biochimica et Biophysica Acta (BBA) - Protein Structure, vol. 405, no. 2, pp. 442–451, 1975.
[38] J. Cohen, Statistical Power Analysis for the Behavioral Sciences, 2nd ed. Lawrence Erlbaum Associates, 1988.
[39] T. Akiba, S. Sano, T. Yanase, T. Ohta, and M. Koyama, “Optuna: A next-generation hyperparameter optimization framework,” in Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2019, pp. 2623–2631.