Credit Risk Prediction: An Application of Federated Learning
Subject Areas : Machine learning
Sara Houshmand
1
*
,
Amir albadvi
2
1 - Department of Industrial Engineering, Faculty of Engineering, Tarbiat Modares University, Tehran, Iran
2 - Department of Industrial Engineering, Faculty of Engineering, Tarbiat Modares University, Tehran, Iran
Keywords: Federated Learning (FL), Credit Risks, Financial Institutions, Heterogeneous Data, Decentralized Federated Learning (DFL) Architecture,
Abstract :
Credit risk is one of the major challenges faced by all financial institutions. Different institutions apply various techniques and models to reduce the risks associated with lending and other financial activities. However, due to the sensitivity of financial data and the diversity of modeling approaches, sharing data among institutions is extremely difficult, often impossible. As a result, improvements in credit risk prediction models typically occur in isolation, hindering collective progress toward higher accuracy and broader effectiveness. Federated learning offers a promising solution by allowing institutions to collaboratively train models without exposing or transferring sensitive data. In this research, we present a federated learning architecture for credit risk prediction that ensures privacy throughout the entire training process. Our results indicate that this approach not only protects data confidentiality but also maintains high predictive accuracy over numerous training rounds, offering a reliable and efficient framework for institutional adoption. The core contribution of this work is the development of a decentralized federated learning (FL) architecture tailored to heterogeneous, non-IID financial data. This framework enhances privacy, scalability, and regulatory compliance, and demonstrates performance advantages over traditional methods. In this article, we demonstrate that using five real-world credit risk datasets, the decentralized FL architecture significantly improves model accuracy (ranging from 71% to 99%) compared to traditional machine learning methods, especially in scenarios where privacy and communication efficiency are essential. While centralized FL achieves the highest average accuracy (up to 83%), the decentralized model provides a strong trade-off between performance and privacy-aware collaboration.
[1] A. Jangir, "German Credit Card Data" [Data set], Kaggle. Available:https://www.kaggle.com/datasets/arunjangir245/german-credit-card. Accessed: Dec. 6, 2024.
[2] A. Oualid, Y. Maleh, and L. Moumoun, “FEDERATED LEARNING TECHNIQUES APPLIED TO CREDIT RISK MANAGEMENT: A SYSTEMATIC LITERATURE REVIEW,” EDPACS, vol. 68, no. 1, pp. 42–56, Jul. 2023, doi: 10.1080/07366981.2023.2241647.
[3] D. Gao, C. Ju, X. Wei, Y. Liu, T. Chen, and Q. Yang, “HHHFL: Hierarchical Heterogeneous Horizontal Federated Learning for Electroencephalography,” arXiv.org, Sep. 11, 2019. http://arxiv.org/abs/1909.05784.
[4] F. Mozaffari, I. Raeesi Vanani, P. Mahmoudian, and B. Sohrabi, “Application of Machine Learning in the Telecommunications Industry: Partial Churn Prediction by using a Hybrid Feature Selection Approach,” Journal of Information Systems and Telecommunication (JIST), vol. 11, no. 44, pp. 331–346, Dec. 2023, doi: https://doi.org/10.61186/jist.38419.11.44.331.
[5] J. Ding, E. Tramel, A. K. Sahu, S. Wu, S. Avestimehr, and T. Zhang, “Federated Learning Challenges and Opportunities: An outlook,” arXiv.org, Feb. 01, 2022. http://arxiv.org/abs/2202.00807.
[6] J. Zhou et al., “A Survey on Federated Learning and its Applications for Accelerating Industrial Internet of Things,” arXiv.org, Apr. 21, 2021. http://arxiv.org/abs/2104.10501.
[7] L. Li, Y. Fan, M. Tse, and K.-Y. Lin, “A review of applications in federated learning,” Computers & Industrial Engineering, vol. 149, p. 106854, Sep. 2020, doi: 10.1016/j.cie.2020.106854.
[8] LaoTse, "Credit Risk Dataset" [Data set], Kaggle. Available: https://www.kaggle.com/datasets/laotse/credit-risk-dataset. Accessed: December 6, 2024.
[9] M. Goutier, C. Diebel, M. Adam, and A. Benlian, “Federated Learning for credit risk assessment,” Proceedings of the ... Annual Hawaii International Conference on System Sciences/Proceedings of the Annual Hawaii International Conference on System Sciences, Jan. 2024, doi: 10.24251/hicss.2023.048.
[10] M. Loukili, F. Messaoudi, and R. El Youbi, “Implementation of Machine Learning Algorithms for Customer Churn Prediction,” Journal of Information Systems and Telecommunication (JIST), vol. 11, no. 43, pp. 196–208, Aug. 2023, doi: https://doi.org/10.61186/jist.34208.11.43.196.
[11] M. Rasouli, "Implementation and comparison of machine learning methods in the credit risk assessment of financial institution customers," 8th International Conference on Industrial Engineering and Systems, 2022.
[12] R. Mehta, "Credit Risk Analysis" [Data set], Kaggle. Available: https://www.kaggle.com/datasets/rameshmehta/credit-risk-analysis?resource=download. Accessed: Dec. 6, 2024.
[13] N. Mohammadi, A. Rezakhani, H. Haj Seyyed Javadi, and P. Asghari, “FLHB-AC: Federated Learning History-Based Access Control Using Deep Neural Networks in Healthcare System,” Journal of Information Systems and Telecommunication (JIST), vol. 12, no. 46, pp. 90–104, Jun. 2024, doi: https://doi.org/10.61186/jist.44500.12.46.90.
[14] P. Rouintan, "Factors affecting credit risk: A case study of bank customers; Keshavarzi Bank," 2006.
[15] P. Sharifi, V. Jain, M. A. Poshtkohi, E. Seyyedi, and V. Aghapour, “Banks Credit Risk Prediction with Optimized ANN Based on Improved Owl Search Algorithm,” Mathematical Problems in Engineering, vol. 2021, pp. 1–10, Dec. 2021, doi: 10.1155/2021/8458501.
[16] Parisrohan, "Credit Score Classification" [Data set], Kaggle. Available: https://www.kaggle.com/datasets/parisrohan/credit-score-classification?resource=download. Accessed: December 6, 2024.
[17] M. Rosuli, "Implementation and comparison of machine learning methods in assessing the credit risk of customers in financial and credit institutions," 8th International Conference on Industrial Engineering and Systems, 2022.
[18] S. Bharati, M. R. H. Mondal, P. Podder, and V. B. S. Prasath, “Federated learning: Applications, challenges and future directions,” International Journal of Hybrid Intelligent Systems, vol. 18, no. 1–2, pp. 19–35, Apr. 2022, doi: 10.3233/his-220006.
[19] S. Jain, "Loan Prediction Based on Customer Behavior" [Data set], Kaggle. Available: https://www.kaggle.com/datasets/subhamjain/loanprediction-based-on-customer-behavior?select=Training+Data.csv. Accessed: Dec. 6, 2024.
[20] TensorFlow, "TensorFlow: An end-to-end open-source machine learning platform." Available: https://www.tensorflow.org/. Accessed: December 6, 2024.
[21] Wst, "Neural network credit scoring models," Computers & Operations Research, vol. 27, no. 11–12, pp. 1131–1152, 2000.
[22] Y. Li, "Credit risk prediction based on machine learning methods," in Proc. 14th Int. Conf. Comput. Sci. Educ. (ICCSE), Aug. 2019, pp. 1011–1013, doi: 10.1109/ICCSE.2019.8845525.
[23] Y. Shastri, "A step-by-step guide to federated learning in computer vision," V7labs.com, V7, Apr. 21, 2023. Available: https://www.v7labs.com/blog/federated-learning-guide. Accessed: June 30, 2023.
[24] Y. Zhao, M. Li, L. Lai, N. Suda, D. Civin, and V. Chandra, “Federated Learning with Non-IID Data,” arXiv (Cornell University), Jan. 2018, doi: 10.48550/arxiv.1806.00582.
[25] Z. Iqbal and H. Y. Chan, "Concepts, key challenges and open problems of federated learning," Int. J. Eng. (IJE), doi: 10.5829/ije.20..a.11.
[26] Z. Wang, J. Xiao, L. Wang, and J. Yao, “A novel federated learning approach with knowledge transfer for credit scoring,” Decision Support Systems, vol. 177, p. 114084, Sep. 2023, doi: 10.1016/j.dss.2023.114084.
[27] Z. Xu, J. Cheng, L. Cheng, X. Xu, and M. Bilal, “MSES credit Risk Assessment model based on federated learning and feature selection,” Computers, Materials & Continua/Computers, Materials & Continua (Print), vol. 75, no. 3, pp. 5573–5595, Jan. 2023, doi: 10.32604/cmc.2023.037287.
[28] H. Zhang, J. Bosch, and H. H. Olsson, "Federated Learning Systems: Architecture Alternatives," in Proc. 27th Asia-Pacific Software Engineering Conf. (APSEC), 2020, pp. 385–394, doi: 10.1109/APSEC51365.2020.00047.
[29] Y. Zhang, H. Xie, B. Bai, W. Yu, L. Li, and Y. Gao, "A survey on federated learning," Knowledge-Based Systems, vol. (Volume not provided).