An Early Warning Credit Risk Prediction Model Based on Metaheuristic Algorithms (Case Study: Bank Sepah)
Keywords:
Credit risk, early warning system, metaheuristic algorithms, machine learning, survival analysis, banking risk managementAbstract
This study aims to develop and validate an intelligent hybrid model for credit risk prediction with early warning capability to support proactive decision-making in banking systems. This data-driven, ex-post facto study was conducted on corporate clients of Bank Sepah. The population included 2,847 firms (2018–2022), from which 340 were selected using proportional stratified sampling. Data were collected from audited financial statements, credit records, and behavioral indicators, and preprocessed through normalization, outlier treatment, and class balancing. Analytical approaches included classical models (logistic regression and Cox survival analysis) and machine learning models (SVM and neural networks). A genetic algorithm was employed for hyperparameter optimization and model aggregation. Model performance was evaluated using accuracy, sensitivity, specificity, F1-score, and AUC . Results indicated that liquidity, profitability, cash flow, and relationship duration significantly reduce default probability and hazard, whereas leverage increases risk. Nonlinear models outperformed linear approaches. The hybrid metaheuristic model achieved the highest AUC and lowest Type II error, demonstrating superior predictive performance and robustness. The survival model also showed strong capability in predicting time-to-default. The proposed framework enhances credit risk prediction accuracy and enables dynamic monitoring and early warning, facilitating more effective and proactive risk management in banking.
Downloads
References
Akhmetshin, E., Abdullayev, I., Makhmudov, S., Klochko, E., & Boltaeva, M. (2026). An Advancing Financial Credit Risk Forecasting Model Using Graph Convolutional Networks for Sustainable Economic Analysis. Engineering, Technology & Applied Science Research, 16(1), 30948-30953. https://doi.org/10.48084/etasr.15057
Arora, N., & Kaur, P. D. (2026). The Confluence of Artificial Intelligence and Credit Risk Assessment: A Scientometric Analysis and Research Frontiers. Technology in Society, 87, 103341. https://doi.org/10.1016/j.techsoc.2026.103341
Aruleba, I. T., & Sun, Y. (2024). Effective Credit Risk Prediction Using Ensemble Classifiers with Model Explanation. IEEE Access. https://doi.org/10.1109/ACCESS.2024.3445308
Bao, W., Xu, K., & Leng, Q. (2024). Research on the Financial Credit Risk Management Model of Real Estate Supply Chain Based on GA-SVM Algorithm. Procedia Computer Science, 243, 900-909. https://doi.org/10.1016/j.procs.2024.09.108
Chang, V., Sivakulasingam, S., Wang, H., Wong, S. T., Ganatra, M. A., & Luo, J. (2024). Credit Risk Prediction Using Machine Learning and Deep Learning: A Study on Credit Card Customers. Risks, 12(11), 174. https://doi.org/10.3390/risks12110174
Deng, Q., Wang, W., & Gu, M. (2025). Enhanced Credit Card Approval Prediction with XGBoost and Metaheuristic Optimization for Reduced Risk. Web Intelligence, 23(4). https://doi.org/10.1177/24056456251356175
Golec, M., & Alabduljalil, M. (2026). Interpretable LLMs for Credit Risk: A Systematic Review and Taxonomy. Expert Systems with Applications, 306, 130941. https://doi.org/10.1016/j.eswa.2025.130941
Gramifar, M., Kabir, G., & Khan, S. A. (2026). Credit Risk Assessment Using Bayesian Networks and Machine Learning Approaches. Advanced Engineering Informatics, 74(Part A), 104638. https://doi.org/10.1016/j.aei.2026.104638
Kunjachen, L. M., & Kavitha, R. (2025). Advancing Cardiovascular Risk Prediction: A Fusion of SVM Models with Fuzzy Logic and the Sugeno Integral. Biomedical Signal Processing and Control, 106, 107774. https://doi.org/10.1016/j.bspc.2025.107774
Kurniawan, R. (2024). Application of Random Forest Algorithm on Credit Risk Analysis. Procedia Computer Science, 245, 740-749. https://doi.org/10.1016/j.procs.2024.10.300
Li, Y., Zhao, R., & An, Y. (2026). A Credit Risk Prediction Model Combining Ensemble Learning and Deep Learning Through Three-Way Decisions. Journal of Big Data, 13, 44. https://doi.org/10.1186/s40537-026-00944
Li, Z., Liang, S., Pan, X., & Pang, M. (2024). Credit Risk Prediction Based on Loan Profit: Evidence from Chinese SMEs. Research in International Business and Finance, 67(Part A), 102155. https://doi.org/10.1016/j.ribaf.2023.102155
Lin, S., Lin, X., & He, X. J. (2025). Credit Risk Identification with Hawkes Processes: Theory and Evidence. The Quarterly Review of Economics and Finance, 103, 102027. https://doi.org/10.1016/j.qref.2025.102027
Machado, M. R., Chen, D. T., & Osterrieder, J. R. (2025). An Analytical Approach to Credit Risk Assessment Using Machine Learning Models. Decision Analytics Journal, 16, 100605. https://doi.org/10.1016/j.dajour.2025.100605
Mahadevan, V., Subramaniam, S., & Srivastava, V. (2026). Carbon Concentration in Bank Portfolios and Efficiency: The Role of Credit Risk and Capitalization. Journal of International Financial Markets, Institutions and Money, 109, 102327. https://doi.org/10.1016/j.intfin.2026.102327
Paz, A., Crawford, B., Monfroy, E., Barrera-Garcia, J., Pena Fritz, A., Soto, R., Cisternas-Caneo, F., & Yanez, A. (2025). Machine Learning and Metaheuristics Approach for Individual Credit Risk Assessment: A Systematic Literature Review. Biomimetics, 10(5), 326. https://doi.org/10.3390/biomimetics10050326
Peng, Q., Zhu, Y., & Wang, G. J. (2025). SCF Credit Risk Assessment with Limited Labeled Data Using Label Propagation Algorithm and Complex Network Approaches. International Review of Financial Analysis, 107, 104619. https://doi.org/10.1016/j.irfa.2025.104619
Plikas, J. H., & Kenourgios, D. (2026). Renewable Energy and Bank Credit Risk: The Mediating Role of Economic Growth. Economic Modelling, 107576. https://doi.org/10.1016/j.econmod.2026.107576
Purnama, M. R., Adriano, B., Lahcene, E., Suppasri, A., Imamura, F., Farid, M., & Adityawan, M. B. (2025). Improving Indonesia's Tsunami Early Warning. Part II: Hybridized Deep Learning and Metaheuristic Algorithm for Forecasting and Optimizing. Ocean Engineering, 333, 121496. https://doi.org/10.1016/j.oceaneng.2025.121496
Rajkumar, K., Jayachandran, P., Chakrapani, K., Magesh, S., & Manikandan, R. (2025). Financial Risk Prediction with Banking Monitoring for Cyber Security Analysis Using Automated Machine Learning. In E. Gangadevi (Ed.), Automated Machine Learning and Industrial Applications. Wiley. https://doi.org/10.1002/9781394272426.ch8
Shao, X., Wang, Z., Mirza, N., & Umar, M. (2026). Fossil Fuel Lending and Transition Risk: Evidence from Provisions and Credit Risk Capital Requirements. International Review of Economics & Finance, 107, 105105. https://doi.org/10.1016/j.iref.2026.105105
Zhu, F., Chen, X., & Li, G. (2022). Multi-Classification Assessment of Personal Credit Risk Based on Stacking Integration. Procedia Computer Science, 214, 605-612. https://doi.org/10.1016/j.procs.2022.11.218
Downloads
Published
Submitted
Revised
Accepted
Issue
Section
License
Copyright (c) 2025 Mohammad Rostami (Author); Yaghoub Pour Karim (Corresponding author); Younes Badavarnahandi, Rasoul Baradaran Hasanzadeh, Mahdi Zeinali (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
