Credit Risk Prediction: An Application of Federated Learning
Subject Areas : Machine learning
Sara Houshmand
1
*
,
Amir albadvi
2
1 - Tarbiat Modares university
2 - Tarbiat Modares University
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. Various institutions have different techniques and models that help decrease the risks linked with lending and other activities conducted by such institutions. However, due to the sensitivity of financial data, as well as diverse approaches, sharing data amongst institutions is very difficult and almost impossible. This means that improvements in models of risk prediction at the organizational level are done individually, thereby setting back progress toward achieving high accuracy and effectiveness. Federated learning is a solution that will enable institutions to collaborate on training models without necessarily having to share sensitive data or even expose sensitive data to other parties. In this sense, we shall provide a credit-risk-prediction-compatible federated learning architecture where data privacy is preserved from the very first step to the end. Our experimental results show that not only does this approach guarantee data privacy, but it also demonstrates high accuracy for a large number of successive rounds, providing it an efficient and reliable solution for any institution to improve its credit risk management while preserving data confidentiality. The novelty of our approach lies in the introduction of a decentralized federated learning (FL) architecture tailored for heterogeneous, non-IID financial data. This innovation improves data privacy, scalability, and security, outperforming existing methods in terms of accuracy and regulatory compliance
[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).