ADVANCING CREDIT RISK ASSESSMENT THROUGH AI-POWERED MACHINE LEARNING METHODOLOGIES
DOI:
https://doi.org/10.65164/m9z5z272Kalit so‘zlar:
Credit Scoring, Probability of Default, Artificial Intelligence, Machine Learning, Financial Risk Assessment, Fairness, Bias, Lending SystemsAbstrak
In today’s world, credit scoring plays a crucial role in financial institutions, banks,
and lending organizations, as it enables the assessment of a customer’s likelihood of repaying a loan
on time. A credit scoring model serves as a predictive tool that estimates the Probability of Default
(PD) for a given borrower based on various financial and behavioral indicators. With the advancement
of artificial intelligence and machine learning techniques, modern credit scoring systems have
become more accurate and efficient in processing large volumes of data. However, these systems may
also introduce challenges related to transparency, fairness, and potential bias in decision-making. This
study examines the fundamentals of credit scoring models, their practical applications, and the
growing role of AI in enhancing predictive performance while addressing ethical considerations. The
findings emphasize the importance of developing reliable, interpretable, and fair credit scoring
systems to ensure sustainable and inclusive financial services.
Havolalar
[1]. IBM. (n.d.). Logistic regression. IBM. https://www.ibm.com/think/topics/logistic- regression
[2]. Wikipedia contributors. (2024, June 16). Logistic regression. In Wikipedia.
https://en.wikipedia.org/wiki/Logistic_regression
[3]. Mathew, A. (2017). Credit scoring using logistic regression [Master’s project, San Jose State
University]. SJSU ScholarWorks. https://doi.org/10.31979/etd.3czc-rhe3
[4]. Jurafsky, D., & Martin, J. H. (2025). Logistic regression (Chapter 5). In Speech and language
processing: An introduction to natural language processing, computational linguistics, and
speech recognition (3rd ed., draft, January 12, 2025). Stanford University.
https://web.stanford.edu/~jurafsky/slp3/5.pdf
[5]. Dembinsky, D., Lucieri, A., Frolov, S., Najjar, H., Watanabe, K., & Dengel, A. (2025, June
18). Unifying VXAI: A systematic review and framework for the evaluation of explainable
AI (arXiv:2506.15408) [Preprint]. arXiv. https://arxiv.org/abs/2506.15408
[6]. Breck, E., Polyzotis, N., Roy, S., Whang, S. E., & Zinkevich, M. (2019). Data validation for
machine learning. In Proceedings of the 2nd SysML Conference (MLSys 2019).
https://mlsys.org/Conferences/2019/doc/2019/167.pdf
[7]. Lloyd, S. (1982). Least squares quantization in PCM. IEEE Transactions on Information
Theory, 28(2), 129–137. https://doi.org/10.1109/TIT.1982.1056489
[8]. MacQueen, J. B. (1967). Some methods for classification and analysis of multivariate
observations. In Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and
Probability, Volume 1: Statistics (pp. 281–297). University of California
