Credit Risk Assessment of Loans Granted by Resalat Charity Bank: Using Machine Learning Models

Authors
mahmood mahmoodzadeh
Masood soufi
Morteza Alipour
Abstract
Despite the growing use of machine learning in credit scoring, many domestic studies still rely mainly on traditional statistical models and static borrower characteristics, while limited attention has been paid to the role of real behavioral, transactional, and repayment-performance data in post-disbursement credit risk monitoring. To address this research gap, this study compares the performance of four stepwise logistic regression models and the LightGBM algorithm in predicting credit default, using data from 119,050 loan facilities granted to individual customers of Resalat Qard al-Hasan Bank during the period between 26 March 2022 and 18 March 20240. The target variable was defined based on repayment delays of more than 90 days, and model performance was evaluated using AUC, Accuracy, Recall, F1-Score, and Balanced Accuracy. The knowledge contribution of this study lies in providing empirical evidence on the effectiveness of real banking data, focusing on behavioral and transactional variables, comparing a classical statistical model with a machine learning algorithm, and assessing model performance in identifying the minority class under imbalanced credit data. The results indicate that repayment-related variables, particularly the number of overdue installments and outstanding debt balance, are the most important predictors of default. Although the fourth logistic regression model achieved a high overall AUC of 0.98, it performed poorly in identifying high-risk customers, with a Recall of only 0.12%. In contrast, LightGBM identified 92.2% of high-risk customers and outperformed logistic regression on imbalance-sensitive evaluation metrics. These findings suggest that, in imbalanced credit datasets, relying solely on AUC and Accuracy can be misleading, while Recall, F1-Score, and Balanced Accuracy are more informative for assessing a model’s ability to detect high-risk borrowers. Therefore, in the post-disbursement monitoring scenario, machine learning algorithms based on behavioral and transactional data can provide a more accurate and reliable framework for credit risk management in Iranian banks.
Keywords
Credit risk
Default
LightGBM
logistic regression
Behavioral and transactional data
Machine Learning Algorithm
− Alamsyah, A., Hafidh, A. A., & Mulya, A. D. (2025). Innovative credit risk assessment: Leveraging social media data for inclusive credit scoring in Indonesia’s fintech sector. MDPI.
− Duarte, J., Siegel, S., & Young, L. (2012). Trust and credit: The role of appearance in peer-to-peer lending. Review of Financial Studies, 25(8), 2455–2484.
− Even Tov, O., Li, X., Wang, H., & همکاران. (2023). The importance of individual-pair lending relationships. SpringerLink.
− Hildebrand, T., Puri, M., & Rocholl, J. (2017). Adverse incentives in crowdfunding. Management Science, 63(3), 587–608.
− Ileberi, E., همکاران. (2024). A machine learning-based credit risk prediction engine system using a stacked classifier and a filter-based feature selection method. SpringerOpen.
− Klatt, M. (2008). Peer to peer lending: Auctioning microcredits over the internet. In Proceedings of the International Conference on Information Systems, Technology and Management, Dubai.
− Li, S., & Ji, X. (2021). The application of the Lasso-Cox model in personal credit risk assessment. Resource Development & Market, 37(2), 129–135.
− Lin, M., Prabhala, N. R., & Viswanathan, S. (2013). Judging borrowers by the company they keep: Friendship networks and information asymmetry in online peer-to-peer lending. Management Science, 59(1), 17–35.
− Liu, Y., Baals, L. J., Osterrieder, J., & Misheva, B. H. (2024). Leveraging network topology for credit risk assessment in P2P lending: A comparative study under the lens of machine learning. UTwente Research.
− Noriega, J. P., Rivera, L. A., & Herrera, J. A. (2023). Machine learning for credit risk prediction: A systematic literature review. MDPI.
− Song, M. Y. (2015). A literature review on the latest research of consumer finance in China. Contemporary Economic Management, 37(4), 6–12.
− Souadda, L. I., Halitim, A. R., Benilles, B., Oliveira, J. M., & Ramos, P. (2025). Optimizing credit risk prediction for peer-to-peer lending using machine learning. MDPI.
− Stein, J. C. (2002). Information production and capital allocation: Decentralized versus hierarchical firms. Journal of Finance, 57(5), 1891–1921.
− Stiglitz, J. E., & Weiss, A. (1981). Credit rationing in markets with imperfect information. American Economic Review, 71(3), 393–410.
− Su, Y., & Cheng, C. (2017). An empirical study on the influencing factors of P2P online borrowers’ default behavior. Journal of Financial Development Research, 1, 70–76.
− Sufi, A. (2007). Information asymmetry and financing arrangements: Evidence from syndicated loans. Journal of Finance, 62(2), 629–668.
− Wang, J., & Li, R. (2023). Asymmetric information in peer-to-peer lending: Empirical evidence from China. EconPapers RePEc.
− Wang, Z., Zhou, C., Liao, L., & Zhang, W. (2020). Informational content of consumption behavior in consumer credit risk evaluation. Economic Research Journal, 55(1), 149–163.
− Zhang, X. (2025). The application of alternative data in credit scoring. Atlantis Press.
− Zhou, G., Ruan, D., & Fan, C. (2021). Loan-reduction and crowding-out effects in asymmetric-information credit markets. Finance Forum, 26(1), 25–36.