Optimizing Multilayer Perceptron with Cost-Sensitive Learning for Addressing Class Imbalance in Credit Card Fraud Detection
Abstract
The increasing use of credit cards in global financial transactions offers significant convenience for consumers and businesses. However, credit card fraud remains a major challenge due to its potential to cause substantial financial losses. Detecting credit card fraud is a top priority, but the primary challenge lies in class imbalance, where fraudulent transactions are significantly fewer than non-fraudulent ones. This imbalance often leads to machine learning algorithms overlooking fraudulent transactions, resulting in suboptimal performance. This study aims to enhance the performance of Multilayer Perceptron (MLP) in addressing class imbalance by employing cost-sensitive learning strategies. The research utilizes a credit card transaction dataset obtained from Kaggle, with additional validation using an e-commerce transaction dataset to strengthen the robustness of the findings. The dataset undergoes preprocessing with RUS and SMOTE techniques to balance the data before comparing the performance of baseline MLP models to those optimized with cost-sensitive learning. Evaluation metrics such as accuracy, recall, F1 score, and AUC indicate that the optimized MLP model significantly outperforms the baseline, achieving an AUC of 0.99 and a recall of 0.6. The model's superior performance is further validated through statistical tests, including Friedman and T-tests. These results underscore the practical implications of implementing cost-sensitive learning in MLPs, highlighting its potential to significantly enhance fraud detection accuracy and offer substantial benefits to financial institutions.
Downloads
References
S. Bagheri, S. Taridashti, H. Farahani, P. Watson, and E. Rezvani, “Multilayer perceptron modeling for social dysfunction prediction based on general health factors in an Iranian women sample,” Front. Psychiatry, vol. 14, no. December, pp. 1–12, 2023, doi: 10.3389/fpsyt.2023.1283095.
Z. Yi et al., “Fraud detection in capital markets: A novel machine learning approach,” Expert Syst. Appl., vol. 231, no. October 2022, p. 120760, 2023, doi: 10.1016/j.eswa.2023.120760.
FBI Springfield, “Internet Crime Complaint Center Releases 2022 Statistics,” https://www.fbi.gov/, 2023. https://www.fbi.gov/contact-us/field-offices/springfield/news/internet-crime-complaint-center-releases-2022-statistics.
M. Habibpour et al., “Uncertainty-aware credit card fraud detection using deep learning,” Eng. Appl. Artif. Intell., vol. 123, no. January, p. 106248, 2023, doi: 10.1016/j.engappai.2023.106248.
Z. Salekshahrezaee, J. L. Leevy, and T. M. Khoshgoftaar, “The effect of feature extraction and data sampling on credit card fraud detection,” J. Big Data, vol. 10, no. 1, 2023, doi: 10.1186/s40537-023-00684-w.
M. Alamri and M. Ykhlef, “Survey of Credit Card Anomaly and Fraud Detection Using Sampling Techniques,” Electron., vol. 11, no. 23, 2022, doi: 10.3390/electronics11234003.
H. Ahmad, B. Kasasbeh, B. Aldabaybah, and E. Rawashdeh, “Class balancing framework for credit card fraud detection based on clustering and similarity-based selection (SBS),” Int. J. Inf. Technol., vol. 15, no. 1, pp. 325–333, 2023, doi: 10.1007/s41870-022-00987-w.
L. Liu, X. Wu, S. Li, Y. Li, S. Tan, and Y. Bai, “Solving the class imbalance problem using ensemble algorithm: application of screening for aortic dissection,” BMC Med. Inform. Decis. Mak., vol. 22, no. 1, pp. 1–16, 2022, doi: 10.1186/s12911-022-01821-w.
P. C. Y. Cheah, Y. Yang, and B. G. Lee, “Enhancing Financial Fraud Detection through Addressing Class Imbalance Using Hybrid SMOTE-GAN Techniques,” Int. J. Financ. Stud., vol. 11, no. 3, 2023, doi: 10.3390/ijfs11030110.
J. Xian, “An Imbalanced Financial Fraud Data Model Based on Improved XGBoost and RUS Boost Fusion Algorithm with Pairwise,” BCP Bus. Manag., vol. 49, pp. 410–419, 2023, doi: 10.54691/bcpbm.v49i.5445.
H. C. Du, L. Lv, H. Wang, and A. Guo, “A novel method for detecting credit card fraud problems,” PLoS One, vol. 19, no. 3 March, pp. 1–26, 2024, doi: 10.1371/journal.pone.0294537.
J. H. Joloudari, A. Marefat, M. A. Nematollahi, S. S. Oyelere, and S. Hussain, “Effective Class-Imbalance Learning Based on SMOTE and Convolutional Neural Networks,” Appl. Sci., vol. 13, no. 6, 2023, doi: 10.3390/app13064006.
I. de Zarzà, J. de Curtò, and C. T. Calafate, “Optimizing Neural Networks for Imbalanced Data,” Electron., vol. 12, no. 12, pp. 1–26, 2023, doi: 10.3390/electronics12122674.
F. Z. El Hlouli, J. Riffi, M. A. Mahraz, A. El Yahyaouy, and H. Tairi, “Credit Card Fraud Detection Based on Multilayer Perceptron and Extreme Learning Machine Architectures,” 2020 Int. Conf. Intell. Syst. Comput. Vision, ISCV 2020, pp. 3–7, 2020, doi: 10.1109/ISCV49265.2020.9204185.
“Credit Card Fraud Detection,” kaggle, 2018. https://www.kaggle.com/datasets/mlg-ulb/creditcardfraud.
N. F. S. Recruitment, “Credit Card Fraud Detection,” kaggle, 2022. https://www.kaggle.com/competitions/nus-fintech-recruitment/data.
P. Gupta, A. Varshney, M. R. Khan, R. Ahmed, M. Shuaib, and S. Alam, “Unbalanced Credit Card Fraud Detection Data: A Machine Learning-Oriented Comparative Study of Balancing Techniques,” Procedia Comput. Sci., vol. 218, pp. 2575–2584, 2023, doi: 10.1016/j.procs.2023.01.231.
M. C. Untoro and M. A. N. M. Yusuf, “Evaluate of Random Undersampling Method and Majority Weighted Minority Oversampling Technique in Resolve Imabalanced Dataset,” IT J. Res. Dev., vol. 8, no. 1, pp. 1–13, 2023, doi: 10.25299/itjrd.2023.12412.
F. Y. Chin, C. A. Lim, and K. H. Lem, “Handling leukaemia imbalanced data using synthetic minority oversampling technique (SMOTE),” J. Phys. Conf. Ser., vol. 1988, no. 1, 2021, doi: 10.1088/1742-6596/1988/1/012042.
P. Mrozek, J. Panneerselvam, and O. Bagdasar, “Efficient resampling for fraud detection during anonymised credit card transactions with unbalanced datasets,” Proc. - 2020 IEEE/ACM 13th Int. Conf. Util. Cloud Comput. UCC 2020, pp. 426–433, 2020, doi: 10.1109/UCC48980.2020.00067.
M. G. Rojas, A. C. Olivera, and P. J. Vidal, “Optimising Multilayer Perceptron weights and biases through a Cellular Genetic Algorithm for medical data classification,” Array, vol. 14, no. April, p. 100173, 2022, doi: 10.1016/j.array.2022.100173.
E. Safari and M. Peykari, “Improving the multilayer Perceptron neural network using teaching-learning optimization algorithm in detecting credit card fraud,” J. Ind. Syst. Eng., vol. 14, no. 2, pp. 159–171, 2022.
R. Saputra, S. Sunardiyo, A. Nugroho, and S. Subiyanto, “Implementasi Multilayer Perceptron Artificial Neural Network untuk Prediksi Konsumsi Energi Listrik PT PLN (Persero) UP3 Salatiga,” Elektrika, vol. 15, no. 2, p. 60, 2023, doi: 10.26623/elektrika.v15i2.6411.
K. A. Rashedi, M. T. Ismail, S. Al Wadi, A. Serroukh, T. S. Alshammari, and J. J. Jaber, “Multi-Layer Perceptron-Based Classification with Application to Outlier Detection in Saudi Arabia Stock Returns,” J. Risk Financ. Manag., vol. 17, no. 2, 2024, doi: 10.3390/jrfm17020069.
T. Deng, “Effect of the Number of Hidden Layer Neurons on the Accuracy of the Back Propagation Neural Network,” Highlights Sci. Eng. Technol., vol. 74, pp. 462–468, 2023, doi: 10.54097/nbra6h45.
I. Araf, A. Idri, and I. Chairi, Cost-sensitive learning for imbalanced medical data: a review, vol. 57, no. 4. Springer Netherlands, 2024.
O. Volk and G. Singer, “An adaptive cost-sensitive learning approach in neural networks to minimize local training–test class distributions mismatch,” Intell. Syst. with Appl., vol. 21, no. December 2023, p. 200316, 2024, doi: 10.1016/j.iswa.2023.200316.
Y. Liu and L. Wu, “Intrusion Detection Model Based on Improved Transformer,” Appl. Sci., vol. 13, no. 10, 2023, doi: 10.3390/app13106251.
J. Liu and Y. Xu, “T-Friedman Test: A New Statistical Test for Multiple Comparison with an Adjustable Conservativeness Measure,” Int. J. Comput. Intell. Syst., vol. 15, no. 1, pp. 1–19, 2022, doi: 10.1007/s44196-022-00083-8.
R. Cao, J. Wang, M. Mao, G. Liu, and C. Jiang, “Feature-wise attention based boosting ensemble method for fraud detection,” Eng. Appl. Artif. Intell., vol. 126, no. PC, p. 106975, 2023, doi: 10.1016/j.engappai.2023.106975.
Copyright (c) 2024 Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright in each article belongs to the author
- The author acknowledges that the RESTI Journal (System Engineering and Information Technology) is the first publisher to publish with a license Creative Commons Attribution 4.0 International License.
- Authors can enter writing separately, arrange the non-exclusive distribution of manuscripts that have been published in this journal into other versions (eg sent to the author's institutional repository, publication in a book, etc.), by acknowledging that the manuscript has been published for the first time in the RESTI (Rekayasa Sistem dan Teknologi Informasi) journal ;
