Operational Risk Prediction in the Banking Industry Using Machine Learning Algorithms

Document Type : Research Paper

Authors

1 Ph.D. Candidate, Department of Industrial Engineering, Faculty of Industrial and Systems Engineering, Tarbiat Modares University, Tehran, Iran.

2 Assistant Prof., Department of Systems and Productivity Management, Faculty of Industrial Engineering & Systems, Tarbiat Modares University, Tehran, Iran.

3 Associate Prof., Department of System and Productivity Management, Faculty of Industrial and Systems Engineering, Tarbiat Modares University, Tehran, Iran.

4 Associate Prof., Department of Information Technology Engineering, Faculty of Industrial and Systems Engineering, Tarbiat Modares University, Tehran, Iran.

10.22059/frj.2025.383851.1007655

Abstract

Objective
This research examines and enhances operational risk management in banks using machine learning algorithms. Effective management of operational risk, which arises from internal or external failures in processes, systems, and personnel, is crucial due to its significant impact on the performance and stability of banks. Its primary goal is to introduce an innovative approach to improving operational risk management in banks through machine learning algorithms. Given the importance of accurately predicting operational risks to prevent potential losses and improve decision-making processes in the banking industry, this research purposes to enhance the accuracy and efficiency of risk prediction models. The focus is on leveraging real-world banking data and evaluating machine learning algorithms to identify the most effective methods for predicting different levels of operational risk.
 
Methods
This research employs machine learning algorithms to predict the occurrence levels of operational risks. The dataset consists of operational risk data from an Iranian bank collected from 2016 to 2023, comprising 4,213 records and 12 features. After preprocessing the data, various machine learning algorithms, including Decision Tree, Random Forest, Support Vector Machine, Logistic Regression, Naïve Bayes, and k-Nearest Neighbors, were utilized for training the models. The data was split into training and test sets in an 80/20 ratio and evaluated using K-fold cross-validation. Model performance was assessed based on metrics such as accuracy, precision, recall, F1-score, and the ROC-AUC curve, with the best model selected for future predictions.
 
Results
The findings show that the use of machine learning algorithms can significantly improve the accuracy of predicting operational risks in banks. In the evaluation of different algorithms, SVM and RF showed the best performance, particularly in classifying the third class (Label 3), where the model's accuracy with the AUC metric was close to one. These results highlight the high capability of these two algorithms in accurately distinguishing between different levels of operational risk. On the other hand, LR and NB demonstrated the weakest performance and failed to predict risks effectively. Overall, the findings indicate that more powerful algorithms like SVM and RF can enhance operational risk management in banks and prevent damage resulting from poor risk management.
 
Conclusion
The results demonstrate that machine learning algorithms can substantially enhance operational risk management in banks. In particular, advanced algorithms such as SVM and RF achieved higher accuracy in predicting operational risks and effectively identified complex and atypical patterns. These technologies, by improving efficiency and reducing the costs associated with risk management, help banks develop better strategies for mitigating operational risks. Therefore, the continuous application of these technologies can enhance banks' performance in operational risk management.

Keywords

Main Subjects

References

 
Abdymomunov, A., Curti, F. & Mihov, A. (2020). US banking sector operational losses and the macroeconomic environment. Journal of Money, Credit and Banking, 52(1), 115 - 144.‏
Afonso, G., Curti, F. & Mihov, A. (2019). Coming to terms with operational risk (No. 20190107). Federal Reserve Bank of New York.‏
Afroz, S., Brennan, M. & Greenstadt, R. (2012, May). Detecting hoaxes, frauds, and deception in writing style online. In 2012 IEEE symposium on security and privacy (pp. 461-475). IEEE.
Akbari, M. & Yazdanian, A. (2023). Machine learning in estimating operational risk coverage capital of banks with a loss distribution Approach. Financial Management Perspective, 13(42), 9-34. doi: 10.48308/jfmp.2023.103948. (in Persian)
Bajalan, S. , Fallahpour, S. and Raeesi, S. (2024). Bank’s Credit Portfolio Optimization Using Actuarial Approach and Artificial Neural Networks. Financial Research Journal, 26(3), 710-733. (in Persian)
Bank for International Settlements (2004). Basel II: International Convergence of Capital Measurement and Capital Standards: a Revised Framework. https://www.bis.org/publ/ bcbs107.htm (06 2004).
Bank for International Settlements (2016). Standardised measurement approach for operational risk - consultative document.
Barakat, A. & Hussainey, K. (2013). Bank governance, regulation, supervision, and risk reporting: Evidence from operational risk disclosures in European banks. International Review of Financial Analysis, 30, 254-273.‏
Basel Committee on Banking Supervision (2006). International convergence of capital measurement and capital standards: A Revised Framework - Comprehensive Version. Bank of International Settl.
Bouveret, A. (2018). Cyber risk for the financial sector: A framework for quantitative assessment. International Monetary Fund.
Cantarella, M., Fraccaroli, N. & Volpe, R. (2023). Does fake news affect voting behaviour?. Research Policy, 52(1), 104628.
Committee of Sponsoring Organizations of the Treadway Commission (COSO). (2017). Enterprise Risk Management: Integrating with Strategy and Performance. New York, NY: COSO.
Crisanto, J. C. & Prenio, J. (2017). Regulatory approaches to enhance banks' cyber-security frameworks. Bank for International Settlements, Financial Stability Institute.‏
Crouhy, M., Galai, D. & Mark, R. (1998). Key steps in building consistent operational risk measurement and management. Operational Risk and Financial Institutions, London: Risk Books, 17(3), 45-62.‏
Drew, J. M. & Farrell, L. (2018). Online victimization risk and self-protective strategies: Developing police-led cyber fraud prevention programs. Police Practice and Research, 19(6), 537-549.
Garg, A., Lilhore, U. K., Ghosh, P., Prasad, D. & Simaiya, S. (2021, August). Machine learning-based model for prediction of student’s performance in higher education. In 2021 8th international conference on signal processing and integrated networks (SPIN) (pp. 162-168). IEEE.
Ghorbani, R., Kordestani, G., Haghighat, H., Ghaemi, M. H. and Azizmohammadlou, H. (2021). Developing a Model for Evaluating the Effectiveness of Risk Management in the Banking Industry. Financial Research Journal, 22(4), 496-520. (in Persian)
González-Carrasco, I., Jiménez-Márquez, J. L., López-Cuadrado, J. L. & Ruiz-Mezcua, B. (2019). Automatic detection of relationships between banking operations using machine learning. Information Sciences, 485, 319-346.
Goutte, C. & Gaussier, E. (2005, March). A probabilistic interpretation of precision, recall and F-score, with implication for evaluation. In European conference on information retrieval (pp. 345-359). Berlin, Heidelberg: Springer Berlin Heidelberg.
Guo, B., Ding, Y., Yao, L., Liang, Y. & Yu, Z. (2020). The future of false information detection on social media: New perspectives and trends. ACM Computing Surveys (CSUR), 53(4), 1-36. doi: 10.1145/3393880
Hoffman, D.G. (2002). Managing Operational Risk: 20 Firmwide Best Practice Strategies, John Wiley & Sons.
Jabbar, M. A., Deekshatulu, B. L. & Chandra, P. (2016). Intelligent heart disease prediction system using random forest and evolutionary approach. Journal of network and innovative computing, 4, 10-10.
Khosh Sima, R. & Shahiki Tash, M. (2013). The impact of credit, operational and liquidity risks on the efficiency of Iran's banking system. Planning and Budgeting, 17(4), 69-95.
(in Persian)
Khrestina, M. P., Dorofeev, D. I., Kachurina, P. A., Usubaliev, T. R. & Dobrotvorskiy, A. S. (2017). Development of algorithms for searching, analyzing and detecting fraudulent activities in the financial sphere.
Liu, X., Wang, X., Su, Q., Zhang, M., Zhu, Y., Wang, Q. & Wang, Q. (2017). A hybrid classification system for heart disease diagnosis based on the RFRS method. Computational and mathematical methods in medicine, 2017(1), 8272091.
Mora Valencia, A. (2010). Cuantificación del riesgo operativo en entidades financieras en Colombia. Cuadernos de Administración, 23(41), 185-211.
Mora-Valencia, A. & Zapata-Jaramillo, W. (2017, July). Quantifying operational risk using the loss distribution approach (lda) model. In Proceedings of the Seventh European Academic Research Conference on Global Business, Economics, Finance and Banking (EAR17Swiss Conference) (pp. 0-10).
Mostafaee, K., Azar, A. & Moghbel, A. (2018). Identification and analysis of operational risks: A fuzzy cognitive map approach. Journal of Asset Management and Financing, 6(4), 1-18. doi: 10.22108/amf.2018.103404.1087. (in Persian)
Naderi, H. & Rastegar, M. A. (2022). Applying the Meta-Synthesis Method in Banking Operational Risk Management Methodology. Journal of Asset Management and Financing, 10(4), 115-132. https://doi.org/10.22108/amf.2023.135765.1767. (in Persian)
Nosrati, H & Pakizeh, K. (2014). Estimation of operating capital reserves in the banking industry. Financial Engineering and Portfolio Management, 5(20), 1-26. (in Persian)
Ostadi, B., Khazayi, S. & Husseinzadeh Kashan, A. (2018). Operational risk Assessment using Bayesian inference with regard to the composition of data sources and the assumption of dependence between experts and internal loss data. Financial Management Strategy, 6(1), 53-72. (in Persian)
Peña, A., Bonet, I., Lochmuller, C., Chiclana, F. & Góngora, M. (2018). An integrated inverse adaptive neural fuzzy system with Monte-Carlo sampling method for operational risk management. Expert Systems with Applications, 98, 11-26.
Pena, A., Patino, A., Chiclana, F., Caraffini, F., Gongora, M., Gonzalez-Ruiz, J. D. & Duque-Grisales, E. (2021). Fuzzy convolutional deep-learning model to estimate the operational risk capital using multi-source risk events. Applied Soft Computing, 107, 107381.‏
Pereira, P. & Pereira, A. (2018). Operational risk management: The basel II.
Poongodi, M., Nguyen, T. N., Hamdi, M. & Cengiz, K. (2023). RETRACTED ARTICLE: A measurement approach using smart-IoT based architecture for detecting the COVID-19. Neural Processing Letters, 55(1), 877-877.
Pun, J. & Lawryshyn, Y. (2012). Improving credit card fraud detection using a meta-classification strategy. International Journal of Computer Applications, 56(10), 41-46.
Rahimi Baghi, A., ArabSalehi, M. and Vaez Barzani, M. (2019). Assessing the Systemic Risk in the Financial System of Iran using Granger Causality Network Method. Financial Research Journal, 21(1), 121-142. (in Persian)
Sadeghi Moghadam, M. R. , Mehregan, M. and Bahrambeig, N. (2025). Reducing Fraud Detection Costs in Credit Card Transactions: An Information Fusion Approach. Financial Research Journal, 27(2), 324-353. doi: 10.22059/frj.2024.338715.1007300 (in Persian)
Sharma, S. & Choudhury, A. R. (2016). Fraud analytics: A survey on bank fraud and fraud prediction using unsupervised learning based approach. International Journal of Innovations in Engineering Research and Technology, 3(3), 1-9.
Simaiya, S., Gautam, V., Lilhore, U. K., Garg, A., Ghosh, P., Trivedi, N. K. & Anand, A. (2021, October). EEPSA: Energy efficiency priority scheduling algorithm for cloud computing. In 2021 2nd international conference on smart electronics and communication (ICOSEC) (pp. 1064-1069). IEEE.
Simaiya, S., Lilhore, U. K., Prasad, D. & Verma, D. K. (2021). MRI brain tumour detection & image segmentation by hybrid hierarchical K-means clustering with FCM based machine learning model. Annals of the Romanian Society for Cell Biology, 25(1), 88-94.
Talebi, M., Kavand, M. & Hosseinpour, M. (2011). Analysis and ranking of operational risks in Islamic banking; Case study: Interest-free banking in Iran. Islamic Economics, 11(44), 157-184. (in Persian)
Tehrani, R., Seraj, M., Foroush Bastani, A. & Fallahpour, S. (2020). Evaluation of the Effect of the Banking Sector Systemic Risk on the Macroeconomic Performance of Iran. Financial Research Journal, 22(3), 297-319. (in Persian)
Tsai, C. F. & Wu, J. W. (2008). Using neural network ensembles for bankruptcy prediction and credit scoring. Expert systems with applications, 34(4), 2639-2649.
Wang, T. & Hsu, C. (2013). Board composition and operational risk events of financial institutions. Journal of Banking & Finance, 37(6), 2042-2051.
Zhou, F., Qi, X., Xiao, C. & Wang, J. (2021). MetaRisk: Semi-supervised few-shot operational risk classification in banking industry. Information Sciences, 552, 1-16.‏
Financial Research Journal
Volume 27, Issue 4
2025
Pages 905-930

Files

Share

How to cite

Statistics