Application of Machine Learning in Financial Credit Risk Management: A systematic review
DOI:
https://doi.org/10.26439/interfases2022.n015.5898Keywords:
machine learning, ML, management, risk, credit, algorithmAbstract
Banking risk management can be divided into the following typology: credit risk, market risk, operational risk, and liquidity risk, the first being the most important type of risk for the financial sector. This article aims to show the advantages and disadvantages of implementing Machine Learning algorithms in credit risk management. A systematic literature review was carried out with the PICo search strategy, and 12 articles were selected. The results show that credit risk is the most relevant. In addition, some of the Machine Learning algorithms have already begun to be implemented; however, some have significant disadvantages, such as not being able to explain the model's operation and are considered a black box. In this sense, it discourages implementation because regulatory bodies require that a model be explainable, interpretable and transparent. Faced with this, it has been decided to make hybrid models between algorithms that are not easy to explain with traditional ones, such as logistic regression. Also, it is presented as an alternative to using methods such as SHAPley Additive exPlanations (SHAP) that help the interpretation of these models.
Downloads
References
Babenko, V., Panchyshyn, A., Zomchak, L., Nehrey, M., Artym-Drohomyretska, Z., & Lahotskyi, T. (2021). Classical machine learning methods in economics research: Macro and micro level examples. WSEAS Transactions on Business and Economics, 18, 209-2017. https://doi.org/10.37394/23207.2021.18.22
Bank for International Settlements. (2005). An explanatory note on the Basel II IRB Risk Weight Functions. Basel Committee on Banking Supervision. https://www.bis.org/bcbs/irbriskweight.htm
BBVA Corporation. (2019, 6 de febrero). Forbes destaca los usos que BBVA hace de la inteligencia artificial. BBVA. https://www.bbva.com/es/forbes-destaca-los-usos-que-bbva-hace-de-la-inteligencia-artificial/
Bhatore, S., Mohan, L., & Reddy, R. (2020). Machine learning techniques for credit risk evaluation: a systematic literature review. Journal of Banking and Financial Technology, 4, 111-138. https://doi.org/10.1007/s42786-020-00020-3
Bussmann, N., Giudici, P., Marinelli, D., & Papenbrock, J. (2020). Explainable AI in fintech risk management. Frontiers in Artificial Intelligence, 1-5. https://doi.org/10.3389/frai.2020.00026
Bussmann, N., Giudici, P., Marinelli, D., & Papenbrock, J. (2021). Explainable machine learning in credit risk management. Computational Economics, 57(1), 203-216. https://doi.org/10.1007/s10614-020-10042-0
Castelvecchi, D. (2016). Can we open the black box of AI? Nature, 538, 20-23. https://doi.org/10.1038/538020a
Columbus, L. (2021, 17 de enero). 76% of enterprises prioritize AI & machine learning in 2021 IT budgets. Forbes. https://www.forbes.com/sites/louiscolumbus/2021/01/17/76-of-enterprises-prioritize-ai--machine-learning-in 2021-it-budgets/?sh=6f9c20c618a3
Cui, H. (2021). Research on Credit Risk Control of Commercial Banks Based on Data Mining Technology. 2021 International Conference on Computer, Blockchain and Financial Development, (pp. 383-386). https://doi.org/10.1109/CBFD52659.2021.00083
Cunningham, P., Cord, M., & Delany, S. J. (2008). Supervised learning. En M. Cord y P. Cunningham (Eds.), Machine learning techniques for multimedia. Cognitive technologies (pp. 21-49). https://doi.org/10.1007/978-3-540-75171-7_2
Dietterich, T. (1997). Machine-learning research. AI Magazine, 18(4), 97-136. https://doi.org/10.1609/aimag.v18i4.1324
Dumitrescu, E., Hué, S., Hurlin, C., & Tokpavi, S. (2021). Machine learning for credit scoring: Improving logistic regression with non-linear decision-tree effects. European Journal of Operational Research, 297(3), 1178-1192. https://doi.org/10.1016/j.ejor.2021.06.053
Elizondo, A. (2003). Medición integral del riesgo de crédito. Limusa.
Enterprise.nxt Staff. (2021, 19 de agosto). The rise of artificial intelligence and machine learning. Hewlett Packard Enterprise. https://www.hpe.com/us/en/insights/articles/the-rise-of-artificial-intelligence-and-machine-learning-2108.html
Fritz-Morgenthal, S., Hein, B., & Papenbrock, J. (2022). Financial risk management and explainable, trustworthy, responsible AI. Frontiers in Artificial Intelligence, 5, 1-14. https://doi.org/10.3389/frai.2022.779799
Ghahramani, Z. (2004). Unsupervised learning. En O. Bousquet, U. von Luxburg, y G. Rätsch (Eds.), Advanced lectures on machine learning. Lecture Notes in Computer Science (vol. 3176, pp. 72-112). Springer. https://doi.org/10.1007/978-3-540-28650-9_5
Giacometti, R., Torri, G., Farina, G., & De Giuli, M. (2020). Risk attribution and interconnectedness in the EU via CDS data. Computational Management Science, 17, 549-567. https://doi.org/10.1007/s10287-020-00385-2
Hui Hoo, Z., Candlish, J., & Teare, D. (2017). What is an ROC curve? Emergency Medicine Journal, 34, 357-359. http://dx.doi.org/10.1136/emermed-2017-206735
IBM. (2018, 26 de diciembre). ¿Qué es machine learning? https://www.ibm.com/pe-es/analytics/machine-learning
KPMG Company. (2021, mayo). With asset quality on the brink, supervisors’ focus on credit risk is growing. https://home.kpmg/xx/en/home/insights/2021/05/with-asset-quality-on-the-brink-supervisors-focus-on-credit-risk-is-growing.html
Leo, M., Sharma, S., & Maddulety, K. (2020). Machine learning in banking risk management: A literature review. Risks, 7(1), 1-22. https://doi.org/10.3390/risks7010029
Mashrur, A., Luo, W., Zaidi, N., & Robles-Kelly, A. (2020). Machine learning for financial risk management: A survey. IEEE Access, 8, 203203-203223. https://doi.org/10.1109/ACCESS.2020.3036322
Milojević, N., & Redzepagic, S. (2021). Prospects of artificial intelligence and machine learning application in banking risk management. Journal of Central Banking Theory and Practice, 10(3), 41-57. https://doi.org/10.2478/jcbtp-2021-0023
Moreno, A., Armengol, E., Béjar, J., Belanche, L., Cortés, U., Gavaldà, R., Gimeno, J. M., López, B., Martín, M. & Sánchez, M. (1994). Aprendizaje automático. Edicions UPC.
Nina, H., Pow-Sang, J. A., & Villavicencio, M. (2021). Systematic mapping of the literature on secure software development. IEEE Access, 9, 36852-36867. https://doi.org/10.1109/ACCESS.2021.3062388
Plawiak, P., Abdar, M., Plawiak, J., Makarenkov, V., & Acharya, U. (2020). DGHNL: A new deep genetic hierarchical network of learners for prediction of credit scoring. Information Sciences, 516, 401-418. https://doi.org/10.1016/j.ins.2019.12.045
SAS: Analytics, Artificial Intelligence and Data Management. (2017). Machine learning and artificial intelligence in a brave new world. https://www.sas.com/en_au/insights/articles/analytics/machine-learning-and-artificial-intelligence-in-a-brave-new-world.html
SAS: Analytics, Artificial Intelligence and Data Management. (2015). Credit risk management - What it is and why it matters. Risk Insights. https://www.sas.com/el_gr/insights/risk-management/credit-risk-management.html
Srinivasa Rao, M., Sekhar, C., & Bhattacharyya, D. (2021). Comparative Analysis of Machine Learning Models on Loan Risk Analysis. Advances in Intelligent Systems and Computing, 1280, 81–90. https://doi.org/10.1007/978-981-15-9516-5_7
Superintendencia de Banca, Seguros y AFP. (s. f.). Métodos basados en calificaciones internas. https://www.sbs.gob.pe/Portals/0/jer/pres_doc_basilea/III%20METODO%20IRB.pdf
Teng, H.-W., & Lee, M. (2020). Estimation procedures of using five alternative machine learning methods for predicting credit card default. En C. Lee, & J. Lee, Handbook of financial econometrics, mathematics, statistics, and machine learning (vol. 4, pp. 3545-3572). https://doi.org/10.1142/9789811202391_0101
Visa, S., Ramsay, B., Ralescu, A., & van der Knaap, E. (2011). Confusion matrix-based feature selection. Proceedings of the 22nd Midwest Artificial Intelligence and Cognitive Science Conference 2011, 120-127.
Zhang, X. D. (2020). A matrix algebra approach to artificial intelligence. Springer.
Zhang, Y., (Ed.). (2010). New Advances in Machine Learning. IntechOpen. https://doi.org/10.5772/225
Downloads
Published
Issue
Section
License
Authors who publish with this journal agree to the following terms:
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under an Attribution 4.0 International (CC BY 4.0) License. that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
Last updated 03/05/21
