Ensemble Machine Learning Models for Predicting Credit Card Transaction Frauds in Banking Sector

Banks are known to incur substantial financial loss every year because of financial fraud in the banks. This can be mitigated through early detection, the development of a counter-strategy, and the recuperation of losses caused by such fraud. This paper presents a proposed ensemble architecture that integrates Long Short-Term Memory (LSTM) and Artificial Neural Network (ANN) to overcome the limitations of class imbalance and multi-layered patterns in transactional data during Credit Card Fraud Detection (CCFD). With the Kaggle CCFD dataset, some preprocessing methods were performed, such as balancing data using the Synthetic Minority Oversampling Technique (SMOTE) and the top features selected using the Random Forest importance, as well as normalizing the values using Min-Max scaling. The proposed ensemble model reached a true rate of 98.67, a true accuracy of 98.51, a recall of 99.89 and an F1-score of 98.34 - far outperforming the traditional classifiers of Decision Trees (DT), Logistic Regression (LR), Naive Bayes (NBs), and K-Nearest Neighbors (KNN). These results demonstrate the ability of the ensemble model to be effective at modeling complex non-linear relationships, minimizing misclassification, and making predictable forecasts in extremely imbalanced data sets. The results highlight that ensemble machine learning (ML) methods have the capacity to augment current fraud detection systems and provide a foundation for future research to create stronger, larger, and safer financial fraud detection systems.

Financial Risk Management Anomaly Detection Fraudulent Transactions Ensemble Machine Learning Data Mining Techniques Classification Algorithms Predictive Analytics Banking Sector Security Credit Card Fraud Detection

References

[1] Z. M. Sanusi, M. N. F. Rameli, and Y. M. Isa, “Fraud schemes in the banking institutions: prevention measures to avoid severe financial loss,” Procedia Economics and Finance, 2015. https://doi.org/10.1016/s2212-5671(15)01088-6.

[2] Y.-J. Chen, W.-C. Liou, Y.-M. Chen, and J.-H. Wu, “Fraud detection for financial statements of business groups,” International Journal of Accounting Information Systems, vol. 32, pp. 1–23, 2019. https://doi.org/10.1016/j.accinf.2018.11.004.

[3] F. Carcillo, Y. A. Le Borgne, O. Caelen, and G. Bontempi, “Streaming active learning strategies for real-life credit card fraud detection: assessment and visualization,” International Journal of Data Science and Analytics, 2018. https://doi.org/10.1007/s41060-018-0116-z.

[4] A. Correa Bahnsen, D. Aouada, A. Stojanovic, and B. Ottersten, “Feature engineering strategies for credit card fraud detection,” Expert Systems with Applications, vol. 51, pp. 134–142, 2016. https://doi.org/10.1016/j.eswa.2015.12.030.

[5] M. S. P., A. Saini, S. Ahmed, and S. D. Sarkar, “Credit card fraud detection using machine learning and data science,” International Journal of Engineering Research, vol. 8, no. 9, 2019. https://doi.org/10.17577/IJERTV8IS090031.

[6] S. V. Suryanarayana, B. Gn, and G. V. Rao, “Machine learning approaches for credit card fraud detection,” International Journal of Engineering and Technology, vol. 7, no. 2, p. 917, 2018. https://doi.org/10.14419/ijet.v7i2.9356.

[7] S. Carta, G. Fenu, D. R. Recupero, and R. Saia, “Fraud detection for e-commerce transactions by employing a prudential multiple consensus model,” Journal of Information Security and Applications, vol. 46, pp. 13–22, 2019. https://doi.org/10.1016/j.jisa.2019.02.007.

[8] A. Dal Pozzolo, G. Boracchi, O. Caelen, C. Alippi, and G. Bontempi, “Credit card fraud detection: a realistic modeling and a novel learning strategy,” IEEE Transactions on Neural Networks and Learning Systems, vol. 29, no. 8, pp. 3784–3797, 2018. https://doi.org/10.1109/TNNLS.2017.2736643.

[9] I. González-Carrasco, J. L. Jiménez-Márquez, J. L. López-Cuadrado, and B. Ruiz-Mezcua, “Automatic detection of relationships between banking operations using machine learning,” Information Sciences, 2019. https://doi.org/10.1016/j.ins.2019.02.030.

[10] S. Taneja, B. Suri, and C. Kothari, “Application of balancing techniques with ensemble approach for credit card fraud detection,” in Proceedings of the International Conference on Computing, Power and Communication Technologies (GUCON), 2019, pp. 753–758.

[11] M. S. Kumar, V. Soundarya, S. Kavitha, E. S. Keerthika, and E. Aswini, “Credit card fraud detection using random forest algorithm,” in Proceedings of the International Conference on Computing and Communications Technologies (ICCCT), 2019, pp. 149–153. https://doi.org/10.1109/ICCCT2.2019.8824930.

[12] A. Sethia, R. Patel, and P. Raut, “Data augmentation using generative models for credit card fraud detection,” in Proceedings of the International Conference on Computing Communication and Automation (ICCCA), 2018. https://doi.org/10.1109/CCAA.2018.8777628.

[13] N. K. Gyamfi and J.-D. Abdulai, “Bank fraud detection using support vector machine,” in Proceedings of the IEEE International Conference on Information Technology, Electronics and Mobile Communication (IEMCON), 2018. https://doi.org/10.1109/IEMCON.2018.8614994.

[14] M. Zamini and G. Montazer, “Credit card fraud detection using autoencoder-based clustering,” in International Symposium on Telecommunication (IST), 2018. https://doi.org/10.1109/ISTEL.2018.8661129.

[15] N. Khare and S. Y. Sait, “Credit card fraud detection using machine learning models and collating machine learning models,” International Journal of Pure and Applied Mathematics, vol. 118, no. 20, pp. 825–838, 2018.

[16] J. O. Awoyemi, A. O. Adetunmbi, and S. A. Oluwadare, “Credit card fraud detection using machine learning techniques: a comparative analysis,” in Proceedings of the IEEE International Conference on Computing, Networking and Informatics (ICCNI), 2017. https://doi.org/10.1109/ICCNI.2017.8123782.

[17] K. Randhawa, C. K. Loo, M. Seera, C. P. Lim, and A. K. Nandi, “Credit card fraud detection using AdaBoost and majority voting,” IEEE Access, 2018. https://doi.org/10.1109/ACCESS.2018.2806420.

[18] S. Shirgave, C. J. Awati, R. More, and R. More, “A review on credit card fraud detection using machine learning,” International Journal of Scientific and Technology Research, vol. 8, no. 10, pp. 1217–1220, 2019.