Enhancing credit card fraud detection: the impact of oversampling rates and ensemble methods with diverse feature selection

Mohamed Akouhar, Abdallah Abarda, Mohamed El Fatini, Mohamed Ouhssini

Abstract


The subject matter of this article is enhancing credit card fraud detection systems by exploring the impact of oversampling rates and ensemble methods with diverse feature selection techniques. Credit card fraud has become a major issue in the financial world, leading to substantial losses for both financial institutions and consumers. As the volume of credit card transactions continues to grow, accurately detecting fraudulent behavior has become increasingly challenging. The goal of this study is to enhance credit card fraud detection by analyzing oversampling rates to select the optimal one for the highest-performing models and using ensemble techniques based on diverse feature selection approaches. The key tasks undertaken in this study include assessing the models’ performance based on accuracy, recall, and AUC scores, analyzing the effect of oversampling using the Synthetic Minority Over-sampling Technique (SMOTE), and proposing an ensemble method that combines the strengths of different feature selection techniques and classifiers. The methods used in this research involve applying a range of machine learning techniques, including logistic regression, decision trees, random forests, and gradient boosting, to an imbalanced dataset where legitimate transactions significantly outnumber fraudulent ones. To address the data imbalance, the researchers systematically investigated the impact of varying oversampling rates using SMOTE. Additionally, they developed an ensemble model that integrates seven feature selection methods with the eXtreme Gradient Boosting (XGB) algorithm. The results show that the application of SMOTE significantly improves the performance of the machine learning models, with an optimal oversampling rate of 20% identified. The XGB model stood out for its exceptional performance, with high accuracy, recall, and AUC scores. Furthermore, the proposed ensemble approach, which combines the strengths of the diverse feature selection techniques and the XGB classifier, further enhances the detection accuracy and system performance compared to the traditional methods. The conclusions drawn from this research contribute to advancing the field of credit card fraud detection by providing insights into the impact of oversampling and the benefits of ensemble methods with diverse feature selection. These insights can aid in the development of more effective and robust fraud detection systems, helping financial institutions and consumers better protect against the growing threat of credit card fraud.

Keywords


credit card fraud; machine learning; fraud detection; ensemble methods; feature selection; SMOTE

Full Text:

PDF

References


Rivera, K., Rohn, C., Donker, J., & Butter, C. Fighting fraud: A never-ending battle. PwC’s Global Economic Crime and Fraud Survey, 2020. 14 p. Available at: https://www.pwc.com/gx/en/forensics/gecs-2020/pdf/global-economic-crime-and-fraud-survey-2020.pdf. (accessed 1.08.2024).

Zhang, Y.-F., Lu, H.-L., Lin, H.-F., Qiao, X.-C., & Zheng, H. The optimized anomaly detection models based on an approach of dealing with imbalanced dataset for credit card fraud detection. Mobile Information Systems, 2022, no. 1, article no. 8027903. DOI: 10.1155/2022/8027903.

Li, L., Liu, Z., Chen, C., Zhang, Y.-L., Zhou, J., & Li, X. A time attention based fraud transaction detection framework. arXiv preprint. DOI: 10.48550/arXiv.1912.11760.

Kültür, Y., & Çağlayan, M. U. Hybrid approaches for detecting credit card fraud. Expert Systems, 2017, no. 34, article no. e12191. DOI: 10.1111/exsy.12191.

Kurshan, E., & Shen, H. Graph computing for financial crime and fraud detection: Trends, challenges and outlook. International Journal of Semantic Computing, 2020, vol. 14, no. 04, pp. 565-589. DOI: 10.1142/S1793351X20300022.

Van Vlasselaer, V., Bravo, C., Caelen, O., Eliassi-Rad, T., Akoglu, L., Snoeck, M., & Baesens, B. Apate: A novel approach for automated credit card transaction fraud detection using network-based extensions. Decision Support Systems, 2015, vol. 75, pp. 38-48. DOI: 10.1016/j.dss.2015.04.013.

Hossain, M. A., Khatun, M. S., Bhuiyan, R. A., & Taslim, M. Handling class imbalance in credit card fraud using various sampling techniques. American Journal of Multidisciplinary Research and Innovation (AJMRI), 2022, vol. 1, no. 4, pp. 1-6. DOI: 10.54536/ajmri.v1i4.633.

Ileberi, E., Sun, Y., & Wang, Z. Performance evaluation of machine learning methods for credit card fraud detection using SMOTE and AdaBoost. IEEE Access, 2021, vol. 9, pp. 165286-165294. DOI: 10.1109/ACCESS.2021.3134330.

Plakandaras, V., Gogas, P., Papadimitriou, T., & Tsamardinos, I. Credit card fraud detection with automated machine learning systems. Applied Artificial Intelligence, 2022, vol. 36, no. 1, article no. e2086354. DOI: 10.1080/08839514.2022.2086354.

Salekshahrezaee, Z., Leevy, J. L., & Khoshgoftaar, T. M. The effect of feature extraction and data sampling on credit card fraud detection. Journal of Big Data, 2023, vol. 10, no. 1, article no. 6. DOI: 10.1186/s40537-023-00684-w.

Fanai, H., & Abbasimehr, H. A novel combined approach based on deep autoencoder and deep classifiers for credit card fraud detection. Expert Systems with Applications, 2023, vol. 217, article no. 119562. DOI: 10.1016/j.eswa.2023.119562.

Buonaguidi, B., Mira, A., Bucheli, H., & Vitanis, V. Bayesian quickest detection of credit card fraud. Bayesian Analysis, 2022, vol. 17, no. 1, pp. 261-290. DOI: 10.1214/20-BA1254.

Ahmad, H., Kasasbeh, B., AL-Dabaybah, B., & Rawashdeh, E. EFN-SMOTE: An effective oversampling technique for credit card fraud detection by utilizing noise filtering and fuzzy C-means clustering. International Journal of Data and Network Science, 2023, vol. 7, no. 4, pp. 1025-1032. DOI: 10.5267/j.ijdns.2023.6.003.

Habibpour, M., Gharoun, H., Mehdipour, M., Tajally, A., Asgharnezhad, H., Shamsi, A., Khosravi, A., & Nahavandi, S. Uncertainty-aware credit card fraud detection using deep learning. Engineering Applications of Artificial Intelligence, 2023, vol. 123, article no. 106248. DOI: 10.1016/j.engappai.2023.106248.

Zhao, Z., & Bai, T. Financial fraud detection and prediction in listed companies using SMOTE and machine learning algorithms. Entropy, 2022, vol. 24, no. 8, article no. 1157. DOI: 10.3390/e24081157.

Mohsen, O. R., Nassreddine, G., & Massoud, M. Credit card fraud detector based on machine learning techniques. Journal of Computer Science and Technology Studies, 2023, vol. 5, no. 2, pp. 16-30. DOI: 10.32996/jcsts.2023.5.2.2.

Aburbeian, A. M., & Ashqar, H. I. Credit card fraud detection using enhanced random forest classifier for imbalanced data. In International Conference on Advances in Computing Research, 2023, Orlando, USA, Springer, pp. 605-616. DOI: 10.1007/978-3-031-33743-7_48.

Tripathy, N., Nayak, S. K., Godslove, J. F., Friday, I. K., & Dalai, S. S. Credit card fraud detection using logistic regression and SMOTE approach. International Journal of Computer and Communication Technology, 2022, vol. 8, no. 4, pp. 38-47. DOI: 10.47893/IJCCT.2022.1438.

Karthikeyan, T., Govindarajan, M., & Vijayakumar, V. An effective fraud detection using competitive swarm optimization based deep neural network. Measurement: Sensors, 2023, vol. 27, article no. 100793. DOI: 10.1016/j.measen.2023.100793.

Malik, E. F., Khaw, K. W., Belaton, B., Wong, W. P., & Chew, X. Y. Credit card fraud detection using a new hybrid machine learning architecture. Mathematics, 2022, vol. 10, no. 9, article no. 1480. DOI: 10.3390/math10091480.

Mienye, I. D., & Sun, Y. A deep learning ensemble with data resampling for credit card fraud detection. IEEE Access, 2023, vol. 11, pp. 30628-30640. DOI: 10.1109/ACCESS.2023.3262020.

Xu, B., Wang, Y., Liao, X., & Wang, K. Efficient fraud detection using deep boosting decision trees. Decision Support Systems, 2023, vol. 175, article no. 114037. DOI: 10.1016/j.dss.2023.114037.

Roseline, J. F., Naidu, G. B. S. R., Pandi, V. S., Rajasree, S. A. A., & Mageswari, N. Autonomous credit card fraud detection using machine learning approach. Computers and Electrical Engineering, 2022, vol. 102, article no. 108132. DOI: 10.1016/j.compeleceng.2022.108132.

Ileberi, E., Sun, Y., & Wang, Z. A machine learning based credit card fraud detection using the GA algorithm for feature selection. Journal of Big Data, 2022, vol. 9, no. 1, article no. 24. DOI: 10.1186/s40537-022-00573-8.

Esenogho, E., Mienye, I. D., Swart, T. G., Aruleba, K., & Obaido, G. A neural network ensemble with feature engineering for improved credit card fraud detection. IEEE Access, 2022, vol. 10, pp. 16400-16414. DOI: 10.1109/ACCESS.2022.3148298.

Chang, V., Doan, L. M. T., Di Stefano, A., Sun, Z., & Fortino, G. Digital payment fraud detection methods in digital ages and industry 4.0. Computers and Electrical Engineering, 2022, vol. 100, article no. 107734. DOI: 10.1016/j.compeleceng.2022.107734.

Shabbir, A., Shabir, M., Javed, A. R., Chakraborty, C., & Rizwan, M. Suspicious transaction detection in banking cyber-physical systems. Computers and Electrical Engineering, 2022, vol. 97, article no. 107596. DOI: 10.1016/j.compeleceng.2021.107596.

Cherif, A., Ammar, H., Kalkatawi, M., Alshehri, S., & Imine, A. Encoder–decoder graph neural network for credit card fraud detection. Journal of King Saud University-Computer and Information Sciences, 2024, vol. 36, no. 3, article no. 102003. Elsevier. DOI: 10.1016/j.jksuci.2024.102003.

Leevy, J. L., Hancock, J., & Khoshgoftaar, T. M. Comparative analysis of binary and one-class classification techniques for credit card fraud data. Journal of Big Data, 2023, vol. 10, no. 1, article no. 118. DOI: 10.1186/s40537-023-00794-5.

Alamri, M., & Ykhlef, M. Hybrid under-sampling and oversampling for handling imbalanced credit card data. IEEE Access, 2024, vol. 12, pp. 14050-14060. DOI: 10.1109/ACCESS.2024.3357091.

Khalid, A. R., Owoh, N., Uthmani, O., Ashawa, M., Osamor, J., & Adejoh, J. Enhancing credit card fraud detection: an ensemble machine learning approach. Big Data and Cognitive Computing, 2024, vol. 8, no. 1, article no. 6. DOI: 10.3390/bdcc8010006.

Dhandore, D., Agrawal, C., & Meena, P. Enhancing credit card fraud detection through advanced ensemble learning techniques and deep learning integration. International Journal of Engineering Applied Science and Management, 2024, vol. 5, no. 9, pp. 1-9. Paper ID: 2024/IJEASM/5/2024/2185.

Zhu, M., Zhang, Y., Gong, Y., Xu, C., & Xiang, Y. Enhancing credit card fraud detection: A neural network and SMOTE integrated approach. arXiv preprint/ DOI: 10.48550/arXiv.2405.00026.

Credit card fraud detection. Available at: https://www.kaggle.com/mlg-ulb/creditcardfraud. (accessed 12 June 2024).




DOI: https://doi.org/10.32620/reks.2025.1.06

Refbacks

  • There are currently no refbacks.