Bridging The Financial Divide: AI-Driven Credit Scoring Models For Underserved Populations
IOSR Journal of Economics and Finance · 2026-01 · 17 (1) · 49-62
DOI: 10.9790/5933-1701034962 ↗Kurz gefasst
Fachartikel in der Zeitschrift IOSR Journal of Economics and Finance, 2026-01.
Abstract (Originalsprache)
Artificial intelligence (AI) has redefined the global credit environment by enhancing the accuracy, inclusivity, and efficiency of lending decisions. This paper critically examines the evolution, architecture, and ethical dimensions of AI-driven credit scoring systems, emphasizing their potential to advance financial inclusion while addressing inherent risks of bias, opacity, and regulatory misalignment. Through an analytical synthesis of recent empirical studies and industry frameworks, this study contrasts traditional credit assessment models which are rooted in static, rule-based approaches, with modern machine learning architectures capable of integrating dynamic, alternative data from mobile money, social transactions, and behavioral patterns. The findings reveal that ensemble learning, neural networks, and hybrid models significantly outperform conventional techniques in predictive accuracy and adaptability, yet persistent challenges remain around explainability, algorithmic fairness, and data governance. Building on comparative analyses, the paper proposes a conceptual framework for inclusive and ethical AI credit scoring, integrating fairness metrics, real-time data pipelines, and bias correction mechanisms to balance performance with accountability. The discussion extends to policy and strategic implications for regulators, fintech innovators, and development agencies, calling for harmonized governance models that align technological innovation with social equity. Lastly, the study argues that the sustainable future of credit access does not only depend on algorithmic sophistication but also on transparent, human-centered systems that embed trust, fairness, and accountability within financial decision-making processes.
Zitieren
APA
(2026). Bridging The Financial Divide: AI-Driven Credit Scoring Models For Underserved Populations. IOSR Journal of Economics and Finance, 17(1), 49-62. https://doi.org/10.9790/5933-1701034962
Vancouver
Bridging The Financial Divide: AI-Driven Credit Scoring Models For Underserved Populations. IOSR Journal of Economics and Finance. 2026;17(1):49-62. doi:10.9790/5933-1701034962
BibTeX
@article{euvimed2026,
title = {Bridging The Financial Divide: AI-Driven Credit Scoring Models For Underserved Populations},
journal = {IOSR Journal of Economics and Finance},
year = {2026},
volume = {17},
number = {1},
pages = {49--62},
doi = {10.9790/5933-1701034962}
}
EUVIMED