MODERNIZING CREDIT SCORING: A STUDY ON THE TRANSITION FROM CONVENTIONAL MODELS TO AI -ENHANCED SYSTEMS
Al-Shodhana · 30.01.2026 · 14 (1) · 631-646
DOI: 10.70644/as.v14.i1.53 ↗Kurz gefasst
Fachartikel in der Zeitschrift Al-Shodhana, online erschienen am 30.01.2026. Verfasst von MS. VANISHREE Y und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
In finance, a credit scoring system is used by banks and financial institutions to evaluate a borrower’s creditworthiness, or the chances of repaying loans promptly. It calculates a numerical score using factors including payment behaviour, credit usage, duration of credit history, credit mix, and recent inquiries. A greater score indicates lower risk, helping borrowers access loans at better rates, while a lower score signals higher risk, often leading to higher interest or rejection. Artificial intelligence (AI) in financial systems has gained considerable focus, especially in credit scoring, where conventional models often fall short in reflecting the complete picture of an individual’s financial behaviour. Conventional models of credit scoring are systems that rely mainly on fixed financial data, such as payment behaviour, unpaid debts, and duration of credit history, to evaluate a borrower’s financial credibility. They often use rigid formulas that may not account for non-traditional factors like digital transactions, utility payments, or changing financial behaviours. As a result, these models can overlook creditworthy individuals with limited credit records and may produce biased or incomplete assessments. Artificial intelligence (AI) is increasingly being integrated into financial systems, drawing notable interest in the field of credit scoring, where conventional methods struggle to reflect the complete range of an individual’s financial activities. This paper explores the design and implementation of AI-based credit scoring models with the goal of advancing financial inclusion. This paper offers an in-depth analysis of how machine learning and big data analytics can be leveraged to create alternative credit scoring approaches. By drawing on varied data sources like social media interactions, usage of mobile phones, transaction records, and utility bill payments, AI-powered models deliver a more comprehensive and adaptive assessment of an individual’s financial trustworthiness. Such unconventional data points provide meaningful insights into spending behaviour, consistency in payments, and personal patterns that conventional models often fail to capture.
Zitieren
APA
Y, M. V., & V, M. C. N. (2026). MODERNIZING CREDIT SCORING: A STUDY ON THE TRANSITION FROM CONVENTIONAL MODELS TO AI -ENHANCED SYSTEMS. Al-Shodhana, 14(1), 631-646. https://doi.org/10.70644/as.v14.i1.53
Vancouver
Y MV, V MCN. MODERNIZING CREDIT SCORING: A STUDY ON THE TRANSITION FROM CONVENTIONAL MODELS TO AI -ENHANCED SYSTEMS. Al-Shodhana. 2026;14(1):631-646. doi:10.70644/as.v14.i1.53
BibTeX
@article{Y2026,
author = {Y, MS. VANISHREE and V, MS. CHAITHRA N},
title = {MODERNIZING CREDIT SCORING: A STUDY ON THE TRANSITION FROM CONVENTIONAL MODELS TO AI -ENHANCED SYSTEMS},
journal = {Al-Shodhana},
year = {2026},
volume = {14},
number = {1},
pages = {631--646},
doi = {10.70644/as.v14.i1.53}
}
EUVIMED