AI impact on traditional credit scoring models

  • Zoran Temelkov
  • Vesna Georgieva Svrtinov
Keywords: AI, credit score, banks, creditworthiness risk assessment

Abstract

Credit scores are an integral part of a bank's lending process because they provide insight into the creditworthiness of each borrower. The traditional credit scoring models offer a standardized approach, but they come with certain shortcomings. AI and machine learning credit scoring models overcome the negative aspects of traditional models while offering banks and borrowers more accurate techniques for risk assessment. Even though AI-powered models are superior to the traditional, they do come with certain challenges related to potential bias, transparency, privacy, and regulatory compliance. It is anticipated that in the future, hybrid credit scoring models will most likely be developed by banks in their efforts to emphasize the advantages and reduce or eliminate the shortcomings of the different models.

Downloads

Download data is not yet available.

References

1. Addy, W. A., Ajayi-Nifise, A. O., Bello, B. G., Tula, S. T., Odeyemi, O., & Falaiye, T. (2024). AI
in Credit Scoring: A Comprehensive Review of Models and Predictive Analytics. Global
Journal of Engineering and Technology Advances, 18(02), pp.118-129. DOI:
https://doi.org/10.30574/gjeta.2024.18.2.0029
2. Anil, K. Sharma, S. & Mahdavi, M. (2021). Machine Learning (ML) Technologies for Digital
Credit Scoring in Rural Finance: A Literature Review. Risks, MDPI, Vol., Issue 11, 192.
https://doi.org/10.3390/risks9110192
3. Duman, E.; Aktas, M.S.; Yahsi, E. (2023). Credit Risk Prediction Based on Psychometric
Data. Computers, Vol. 12, no. 12: 248. https://doi.org/10.3390/computers12120248
4. FasterCapital (2024, February, 21). Understanding an Alternative Credit Scoring Model 2.
FasterCapital. Available at: https://fastercapital.com/content/Understanding-an-AlternativeCredit-Scoring-Model-2.html#The-Limitations-of-Traditional-Credit-Scoring.html
5. Gsenger, R. & Strle, T. (2021). Trust, automation bias and aversion: algorithmic
decisionmaking in the context of credit scoring. In Interdisciplinary Description of Complex
Systems: INDECS, 19(4), 540-558. https://www.doi.org/10.7906/indecs.19.4.7
6. Hong Kong Monetary Authority (2020). Alternative Credit Scoring of Micro-, Small and
Medium-sized Enterprise. Applied Science and Technology Research Institute – ASTRI.
9
7. Huang, Y. et al. (2020). Fintech Credit Risk Assessment for SMEs: Evidence from China. IMF
Working Paper, WP/20/193.
8. Hurlin, C. Pérignon, C. & Saurin, S. (2024). The Fairness of Credit Scoring Models.
https://doi.org/10.48550/arXiv.2205.10200
9. Khemakhem, S. & Boujelbene, Y. (2017). Artificial Intelligence for Credit Risk Assessment:
Artificial Neural Network and Support Vector Machines. ACRN Oxford Journal of Finance and
Risk Perspectives 6.2, pp. 1- 17.
10. Langenbucher, K. & Corcoran, P. (2022). Responsible AI Credit Scoring – A Lesson from
Upstart.com. De Gruyter. DOI https://doi.org/10.1515/9783110749472-006
11. Leo, M., Sharma, S., & Maddulety, K. (2019). Machine Learning in Banking Risk Management:
A Literature Review. Risks. MDPI, Vol., 7, Issue 1, 29; https://doi.org/10.3390/risks7010029
12. Marletta, A. (2022). The evaluation of credit risk using survival models: an application on
Italian SMEs. Statistica & Applicazioni - Vol. XIX, n. 2, pp. 161-178.
13. Milkau, U. (2021). Algorithmic Credit Scoring in the USA, Europe and China: Between
Regulation and ‘Petrification. Contribution to the Virtual Workshop on AI & Finance, Oct. 29 /
Nov. 12, DHBW Moschbach. ISBN 978-3-943656-16-9.
14. Oualid, A., Hansali, A., Balouki, Y., & Moumoun, L. (2022). Application of Machine Learning
Techniques for Credit Risk Management: A Survey. Advances in Information, Communication
and Cybersecurity. Springer. DOI: 10.1007/978-3-030-91738-8_18
15. Sadok, H. Sakka, F. & El Hadi El Maknouzi, M. (2022). Artificial intelligence and bank credit
analysis: A review. Cogent Economics & Finance, 10:1, 2023262, DOI:
https://doi.org/10.1080/23322039.2021.202326
16. Shenoy, R.R., Mohammed, M., & Fiaidhi, J. (2018). International Journal of Smart Business
and Technology. Vol.6, No.1, pp. 49-68. http://dx.doi.org/10.21742/ijsbt.2018.6.1.05
17. Simumba, N., Okami, S., Kodaka, A. & Kohtake, N. (2018). Alternative Scoring Factors using
Non-Financial Data for Credit Decisions in Agricultural Microfinance. In IEEE International
Systems Engineering Symposium (ISSE) (pp. 1-8).
https://www.doi.org/10.1109/SysEng.2018.8544442
18. Tyagi, S. (2022). Analyzing Machine Learning Models for Credit Scoring with Explainable AI
and Optimizing Investment Decisions. American International Journal of Business
Management. Volume 5, Issue 01, ISSN- 2379-106X, pp. 05-19.
19. Wendel, C.B. & Harvey, M. (2006). SME Credit Scoring: Key Initiatives, Opportunities, and
Issues. The World Bank Group. Access Finance, Issue, No. 10.
20. White, S. (2023, April, 23). The Role of Artificial Intelligence and Machine Learning in Credit
Scoring. CreditInfo. Available at: https://chronicle.creditinfo.com/2023/04/26/the-role-ofartificial-intelligence-and-machine-learning-in-credit-scoring/
21. Wijaya, T. & Nidhal, M. (2023). International Experiences with Innovative Credit Scoring.
Center for Indonesian Policy Studies Discussion Paper No. 14.
22. Xhumari, E & Haloci, S. (2023). A comparative study of Credit Scoring and Risk Management
Techniques in Fintech: Machine Learning vs. Regression Analysis. CEUR Workshop
Proceedings, RTA-CSIT 2023, April 26–27
Published
2024-05-23
Section
Banking and Finance