Artificial Intelligence And Machine Learning Predictive Models In Financial Risk Management: A Comparative Study Of Iraqi Banks
Abstract
This study deals with assessing the feasibility and effectiveness of using AI and ML models in Iraqi banks for financial risk management, which are currently facing a critical situation regarding the non-performing loan ratio, reaching 14.2%, compared to 4.5% on average in the MENA region.
This research follows a mixed-methods research design, and this paper analyzes 10 banks from Iraq, which constitute 75% of industry assets, using various machine learning models on 125,487 loans between 2015 and 2024, and 38 interviews were conducted on stakeholders. Various machine learning models have been applied, such as Random Forest, XGBoost, Neural Networks, and LSTM.
Moreover, the results show that ML techniques were significantly better than traditional techniques in terms of accuracy, i.e., 84.6% vs. 68.4% (+16.2% pp) for the classification, 71.8% default detection vs. 42.8% (+29.0% pp), and AUC-ROC 0.885 vs. 0.642, at a p < 0.001 level. The economic gains show that the system can win 227.2 million dollars annually or cut 50.6% error costs. The cost savings from the system implementation will be 3 million dollars over a period of 3 years, rewarding a NPV and IRR of 1.9 million dollars and 54.3%, respectively.
The research validates three research hypotheses: technological readiness and data quality affect the feasibility of the implementation (R²=0.847), ML models have a significant superiority over conventional models (d=2.83), and a phased implementation approach can achieve a success rate of 85%.
The study identified that the key factors to the success of the implementation are: executive support (β=0.68), data quality
Keywords
Full Text:
PDFReferences
Baesens, B., Van Gestel, T., Viaene, S., Stepanova, M., Suykens, J., & Vanthienen, J. (2003). Benchmarking state-of-the-art classification algorithms for credit scoring. Journal of the Operational Research Society, 54(6), 627-635.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.
Hastie, T., Tibshirani, R., & Friedman, J. (2009). The elements of statistical learning: Data mining, inference, and prediction (2nd ed.). Springer.
Hull, J. C. (2018). Risk management and financial institutions (5th ed.). John Wiley & Sons.
James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An introduction to statistical learning with applications in R. Springer.
Molnar, C. (2022). Interpretable machine learning: A guide for making black box models explainable (2nd ed.). Lulu.com.
Bharti, R., Khamparia, A., Shabaz, M., Dhiman, G., Pande, S., & Singh, P. (2022). Prediction of heart disease using a combination of machine learning and deep learning. Computational Intelligence and Neuroscience, 2022, Article 8387680.
Brown, I., & Mues, C. (2012). An experimental comparison of classification algorithms for imbalanced credit scoring data sets. Expert Systems with Applications, 39(3), 3446-3453.
Cao, L. (2020). AI in finance: A review. Social Science Research Network. Available at SSRN: https://ssrn.com/abstract=3647625
De Lange, P. E., Melsom, B., Vennerød, C. B., & Westgaard, S. (2022). Explainable AI for credit assessment in microfinance. Journal of Risk and Financial Management, 15(12), 556.
Fischer, T., & Krauss, C. (2018). Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research, 270(2), 654-669.
Gu, S., Kelly, B., & Xiu, D. (2020). Empirical asset pricing via machine learning. Review of Financial Studies, 33(5), 2223-2273.
Khandani, A. E., Kim, A. J., & Lo, A. W. (2010). Consumer credit-risk models via machine-learning algorithms. Journal of Banking & Finance, 34(11), 2767-2787.
Kim, H. Y., & Won, C. H. (2018). Forecasting the volatility of stock price index: A hybrid model integrating LSTM with multiple GARCH-type models. Expert Systems with Applications, 103, 25-37.
Kristjanpoller, W., & Minutolo, M. C. (2018). A hybrid volatility forecasting framework integrating GARCH, artificial neural network, genetic algorithm and the wavelet transform. Expert Systems with Applications, 109, 1-11.
Lessmann, S., Baesens, B., Seow, H. V., & Thomas, L. C. (2015). Benchmarking state-of-the-art classification algorithms for credit scoring: An update of research. European Journal of Operational Research, 247(1), 124-136.
Moscatelli, M., Narizzano, S., Palumbo, F., & Viggiano, G. (2020). Corporate default forecasting with machine learning. Expert Systems with Applications, 161, 113567.
Sirignano, J., Sadhwani, A., & Giesecke, K. (2016). Deep learning for mortgage risk. Journal of Financial Econometrics, 19(2), 313-368.
Basel Committee on Banking Supervision. (2019). Principles for the sound management of operational risk. Bank for International Settlements.
Basel Committee on Banking Supervision. (2022). Principles for the effective management and supervision of climate-related financial risks. Bank for International Settlements.
Deloitte. (2019). Becoming an AI-fueled organization: A global survey on artificial intelligence in financial services. Deloitte Center for Financial Services.
International Monetary Fund. (2023). Republic of Iraq: 2023 Article IV consultation—Press release; Staff report; and statement by the executive director for Iraq. IMF Country Report No. 23/265.
McKinsey & Company. (2020). Global banking annual review 2020: A test of resilience. McKinsey & Company.
PwC. (2021). Global artificial intelligence study: Exploiting the AI revolution. PricewaterhouseCoopers.
World Bank. (2023). Iraq economic monitor: Toward a prosperous and inclusive Iraq. World Bank Group.
Central Bank of Iraq. (2020). Banking supervision report 2020. Baghdad: Central Bank of Iraq.
Central Bank of Iraq. (2022). Annual statistical bulletin 2022. Baghdad: Central Bank of Iraq.
Central Bank of Iraq. (2023). Financial stability report 2023. Baghdad: Central Bank of Iraq.
Central Bank of Iraq. (2024). Directives on risk management in Iraqi banks (Circular No. 12/2024). Baghdad: Central Bank of Iraq.
Al-Shammari, M., Hassan, A., & Al-Obaidi, Z. (2021). Challenges of Basel III implementation in Iraqi private banks. In Proceedings of the International Conference on Economics and Business Management (pp. 234-248). Istanbul, Turkey.
Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785-794). ACM.
Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735-1780.
Al-Yasiri, A. K. (2017). Efficiency measurement of Iraqi banks using data envelopment analysis [Doctoral dissertation, University of Baghdad]. Iraqi Academic Scientific Journals Database.
Hassan, M. A. (2019). Determinants of credit risk in Iraqi banking sector: An empirical analysis [Master's thesis, University of Baghdad]. Iraqi Digital Library.
Iraq Stock Exchange. (2024). Historical market data 2015-2024. Retrieved from http://www.isx-iq.net
International Monetary Fund. (2024). World economic outlook database. Retrieved from https://www.imf.org/external/pubs/ft/weo/2024/01/weodata/index.aspx
Trading Economics. (2024). Iraq economic indicators. Retrieved from https://tradingeconomics.com/iraq/indicators
World Bank Open Data. (2024). Iraq country data. Retrieved from https://data.worldbank.org/country/iraq
Basel Committee on Banking Supervision. (2006). International convergence of capital measurement and capital standards: A revised framework (Basel II). Bank for International Settlements.
Basel Committee on Banking Supervision. (2017). Basel III: Finalising post-crisis reforms. Bank for International Settlements.
Financial Stability Board. (2017). Artificial intelligence and machine learning in financial services: Market developments and financial stability implications. FSB.
Chen, T., He, T., Benesty, M., Khotilovich, V., Tang, Y., Cho, H., ... & Zhou, T. (2023). XGBoost: Extreme gradient boosting (R package version 1.7.5). Retrieved from https://CRAN.R-project.org/package=xgboost
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., ... & Duchesnay, É. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825-2830.
Python Software Foundation. (2023). Python language reference, version 3.11. Retrieved from http://www.python.org
Accenture. (2020). Banking technology vision 2020: The future is now—Tech leaders shape the next decade. Accenture.
Capgemini & Efma. (2021). World retail banking report 2021: Transformation and trust in the age of AI. Capgemini Research Institute.
Deloitte. (2022). Banking and capital markets outlook 2022: Reimagining transformation. Deloitte Center for Financial Services.
Ernst & Young. (2020). How can AI transform risk management in financial services? EY Global Financial Services.
KPMG. (2021). Frontiers in finance: Transforming risk management with AI and machine learning. KPMG International.
European Banking Authority. (2020). Report on big data and advanced analytics. EBA/Rep/2020/01.
Financial Conduct Authority (UK). (2022). Artificial intelligence and machine learning in financial services. FCA.
Monetary Authority of Singapore. (2021). Principles to promote fairness, ethics, accountability and transparency (FEAT) in the use of artificial intelligence and data analytics in Singapore's financial sector. MAS.
Office of the Comptroller of the Currency (USA). (2021). Model risk management: Comptroller's handbook. OCC.
The Economist. (2023, June 15). How artificial intelligence is revolutionising finance. The Economist, 447(9349), 18-20.
Financial Times. (2022, March 10). Banks turn to AI to improve risk management. Financial Times.
Reuters. (2023, September 8). Iraq's banking sector faces modernization challenges. Reuters News Service.
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5-32.
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16, 321-357.
Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29(5), 1189-1232.
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436-444.
Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems (pp. 4765-4774).
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). "Why should I trust you?" Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 1135-1144).
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
ISSN 1305-578X (Online)
Copyright © 2005-2022 by Journal of Language and Linguistic Studies