A COMPARATIVE STUDY OF TRADITIONAL AND AI-POWERED MODELS FOR EVALUATION OF CREDITWORTHINESS

Assoc. Prof. Kamelia Assenova, PhD

Department of Economics UNWE, Sofia

E-mail: kamelia_a@yahoo.com

Nikolay Petrov, PhD Student

Department of Economics and International Relations “Angel Kanchev” Univesity of Ruse

E-mail: npetrov@uni-ruse.bg

Abstract

Due to the weak development of the financial market in Bulgaria, most companies finance their investments with bank loans. The households also use bank loans to purchase durable goods. The individuals balance their cash inflows and outflows through bank loans. This requires the bank to assess on each loan request the likelihood that a customer or firm will meet its obligations, which is essential for the stability of the financial system and for minimizing losses from non-performing loans. The creditworthiness assessment is a key component in credit risk management and financial decision making by both banks and other lending institutions. Traditional models for evaluation of creditworthiness are a solid foundation and are still widely used today - especially in more conservative lending institutions. With the growth of data, technology and demands for greater accuracy, new techniques (machine learning, AI) are also emerging - but this does not refuse traditional approaches, but rather complements them. For borrower assessment, it is important to combine both financial/balance sheet information and qualitative aspects (governance, business environment, guarantees)- which the traditional approach does, albeit with limitations. By the integrated mechanism has a balance between accuracy, speed and confidence in the decision-making process.

Keywords

Banks, credits, creditworthiness, AI models

REFERENCES

Abdou Hussein & John Pointon, (2011.). "Credit Scoring, Statistical Techniques And Evaluation Criteria: A Review Of The Literature," Intelligent Systems in Accounting, Finance and Management, John Wiley & Sons, Ltd., vol. 18(2-3), pages 59-88, DOI: 10.1002/isaf.325
Altman, Edward I. 1968). "Financial Ratios, Discriminant Analysis and the Prediction of Corporate Bankruptcy". Journal of Finance. 23 (4): 189-209. doi:10.1111/j.1540-6261.1968.tb00843.x
Gautam, S., & Mittal, P. (2022a). Comprehensive Analysis of Privacy Preserving Data Mining Algorithms for Future Develop Trends. International Research Journal of Computer Science, 9(10), 367-374. https://doi.org/10.26562/irjcs.2022.v0910.01
Gautam, S., & Mittal, P. (2022b). Comprehensive Analysis of Privacy Preserving Data Mining Algorithms for Future Develop Trends. International Research Journal of Computer Science, 9(10), 367-374. https://doi.org/10.26562/irjcs.2022.v0910.01
Jora, R. B., Sodhi, K. K., Mittal, P., & Saxena, P. (2022). Role of Artificial Intelligence (AI) In meeting Diversity, Equality and Inclusion (DEI) Goals. 8th International Conference on Advanced Computing and Communication Systems, ICACCS 2022, 1687-1690. https://doi.org/10.1109/ICACCS54159.2022.9785266
Gambacorta,Leonardo & Fabiana Sabatini & Stefano Schiaffi (2025).Artificial intelligence and relationship lending. BIS Working Papers. No 1244. 36 p. 19 February 2025
Gambacorta, Leonardo, Yiping Huang, Han Qiu, and Jingyi Wang (2024). “How Do Machine Learning and Non-Traditional Data Affect Credit Scoring? New Evidence from a Chinese Fintech Firm.” Journal of Financial Stability 73, 101284
Louzada Francisco , Anderson Ara, Guilherme B. Fernandes(2016)„Classification methods applied to credit scoring: A systematic review and overall comparison“. Surveys in Operations Research and Management Science. Volume 21, Issue 2, December 2016, Pages 117-134. https://doi.org/10.1016/j.sorms.2016.10.001
Marqués A I & V García & J S Sánchez, 2013. "A literature review on the application of evolutionary computing to credit scoring," Journal of the Operational Research Society, Palgrave Macmillan;The OR Society, vol. 64(9), pages 1384-1399
C. Onay & E. Öztürk (2018) A review of credit scoring research in the age of Big Data. Journal of Financial Regulation and Compliance, Vol. 26, Issue 3, pp. 382-405
Paudel, R. (2024). The Impact of Automation and Artificial Intelligence (AI) on Leadership and the Workforce. Indonesian Journal of Banking and Financial Technology, 2(2), 109-124. https://doi.org/10.55927/fintech.v2i2.8904
Rogojan Luana Cristina & Croicu Andreea Elena & Iancu Laura Andreea, (2023). "Modern Approaches in Credit Risk Modeling: A Literature Review". Proceedings of the International Conference on Business Excellence, Sciendo, vol. 17(1), pages 1617-1627, doi: 10.2478/picbe-2023-0145
Smith, J., & Johnson, E. (2020). Artificial Intelligence Techniques for Credit Risk Assessment:A Review. International Journal of Intelligent Systems, 5(30), 789-305.
Soori, M., Arezoo, B., & Dastres, R. (2023). Internet of Things for Smart Factories in Industry 4.0, a Review. Internet of Things and Cyber-Physical Systems, 3, 192-204. https://doi.org/10.1016/j.iotcps.2023.04.006.