A Comprehensive Review of Machine Learning Techniques for Credit Card Fraud Detection: Addressing Data Imbalance and Model Performance
Keywords:
Anomaly detection, Credit card fraud, Data imbalance, Financial security, Fraud detection, Machine learningAbstract
Credit card fraud continues to pose significant challenges within the financial sector, presenting serious threats to both consumers and financial institutions. With the rapid growth of digital transactions, the demand for highly accurate and real-time fraud detection systems has become more critical than ever. This review paper provides a comprehensive examination of the diverse techniques and methodologies developed to identify fraudulent credit card transactions. It evaluates their applicability, effectiveness, and adaptability in rapidly changing transaction ecosystems. The review organizes existing literature according to various machine learning paradigms and detection approaches, emphasizing the roles of pattern recognition, anomaly detection, and behavioral analysis in mitigating fraud. Key issues such as class imbalance, the constantly evolving tactics of fraudsters, and the scarcity of labeled datasets are thoroughly discussed. The paper further explores commonly used performance metrics and evaluation criteria for assessing the efficacy of fraud detection models. Attention is also given to essential components such as data preprocessing techniques, feature selection strategies, and the scalability of detection systems, all of which significantly influence detection precision. The paper concludes by outlining current research gaps and recommending future directions. These include the design of more adaptive, interpretable, and privacy-conscious detection frameworks that are capable of maintaining high performance in real-time, large-scale operational environments.
References
A. Kundu, S. Panigrahi, S. Sural, and A. K. Majumdar, “Blast-SsahA Hybridization for Credit Card Fraud Detection,” IEEE Transactions on Dependable and Secure Computing, vol. 6, no. 4, pp. 309–315, Oct. 2009, doi: https://doi.org/10.1109/tdsc.2009.11.
A. Shen, R. Tong, and Y. Deng, "Application of classification models on credit card fraud detection," June 2007. https://doi.org/10.1109/ICSSSM.2007.4280163
Ghosh and D.L. Reilly, “Credit Card Fraud Detection with a Neural-Network,” Proc. 27th Hawaii International Conference on System Sciences: Information Systems: Decision Support and Knowledge-Based Systems, vol. 3, pp. 621-630, 1994. https://doi.org/10.1109/HICSS.1994.323314
K. Deng, R. Zhang, D. Zhang, W. Jiang, X. Niu, and H. Guo, “Analysis and Study on Detection of Credict Fraud in E-Commerce,” 2011 International Conference on Future Computer Sciences and Application, pp. 12–15, Jun. 2011, doi: https://doi.org/10.1109/icfcsa.2011.10.
L. Seyedhossein and M. R. Hashemi, “Mining information from credit card time series for timelier fraud detection,” 2010 5th International Symposium on Telecommunications, Dec. 2010, doi: https://doi.org/10.1109/istel.2010.5734099.
L. Delamaire, H. A. Abdou, and J. Pointon, “Credit card fraud and detection techniques: A review,” ResearchGate, 2009. https://www.researchgate.net/publication/40227011_Credit_card_fraud_and_detection_techniques_A_review
F. Alonso and X. Wang, “Comparison with Parametric Optimization in Credit Card Fraud Detection,” 2008 Seventh International Conference on Machine Learning and Applications, Dec. 2008, doi: https://doi.org/10.1109/icmla.2008.59.
M. D. H. Mahdi, K. M. Rezaul, and M. A. Rahman, “Credit Fraud Detection in the Banking Sector in the UK: A Focus on E-Business,” IEEE Xplore, Feb. 01, 2010. https://ieeexplore.ieee.org/abstract/document/5432793-Credit
M. Pejić-Bach, “Invited Paper: Profiling Intelligent Systems Applications in Fraud Detection and Prevention: Survey of Research Articles,” International Conference on Intelligent Systems, Modelling and Simulation, Jan. 2010, doi: https://doi.org/10.1109/isms.2010.26.
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: https://doi.org/10.3390/bdcc8010006.
X. Feng and S.-K. Kim, “Novel Machine Learning Based Credit Card Fraud Detection Systems,” Mathematics, vol. 12, no. 12, pp. 1869–1869, Jun. 2024, doi: https://doi.org/10.3390/math12121869.
D. T. Mosa, S. E. Sorour, A. A. Abohany, and F. A. Maghraby, “CCFD: Efficient Credit Card Fraud Detection Using Meta-Heuristic Techniques and Machine Learning Algorithms,” Mathematics, vol. 12, no. 14, pp. 2250–2250, Jul. 2024, doi: https://doi.org/10.3390/math12142250.
E. F. Malik, K. W. Khaw, B. Belaton, W. P. Wong, and X. Chew, “Credit Card Fraud Detection Using a New Hybrid Machine Learning Architecture,” Mathematics, vol. 10, no. 9, p. 1480, Apr. 2022, doi: https://doi.org/10.3390/math10091480.
I. Mekterović, M. Karan, D. Pintar, and L. Brkić, “Credit Card Fraud Detection in Card-Not-Present Transactions: Where to Invest,” Applied Sciences, vol. 11, no. 15, p. 6766, Jul. 2021, doi: https://doi.org/10.3390/app11156766.
E. Strelcenia and S. Prakoonwit, “Improving Classification Performance in Credit Card Fraud Detection by Using New Data Augmentation,” AI, vol. 4, no. 1, pp. 172–198, Jan. 2023, doi: https://doi.org/10.3390/ai4010008.
I. D. Mienye and T. G. Swart, “A Hybrid Deep Learning Approach with Generative Adversarial Network for Credit Card Fraud Detection,” Technologies, vol. 12, no. 10, p. 186, Oct. 2024, doi: https://doi.org/10.3390/technologies12100186.
M. Li and J. Walsh, “FedGAT-DCNN: Advanced Credit Card Fraud Detection Using Federated Learning, Graph Attention Networks, and Dilated Convolutions,” Electronics, vol. 13, no. 16, p. 3169, Aug. 2024, doi: https://doi.org/10.3390/electronics13163169.
A. Alharbi, A.Alshammari, O. D. Okon, “A Novel text2IMG Mechanism of Credit Card Fraud Detection: A Deep Learning Approach,” Electronics, vol. 11, no. 5, p. 756, Mar. 2022, doi: https://doi.org/10.3390/electronics11050756.
