AI-Driven Credit Scoring and Financial Inclusion: Performance, Fairness, And Transparency in Alternative-Data Lending

Arav Vikas Dang

AI-Driven Credit Scoring and Financial Inclusion: Performance, Fairness, And Transparency in Alternative-Data Lending

Author(s)	Mr. Arav Vikas Dang
Country	India
Abstract	Access to formal credit remains uneven, especially for individuals with limited or no credit histories. Such “thin-file” borrowers are routinely excluded from conventional bureau-based credit scoring that depends on past repayment records and formal financial footprints. Advances in artificial intelligence (AI) and machine learning (ML) allow lenders to incorporate richer, consented alternative data into credit assessment, offering a pathway to improve both default prediction and financial inclusion. This paper evaluates whether AI-driven credit scoring models improve loan default prediction and expand credit access compared with traditional statistical approaches. Using a combination of bureau variables and alternative indicators—including mobile payments, UPI transaction stability, utility-bill regularity, and telecom-based behavioral aggregates—the study examines predictive performance, approval lift among underserved borrowers, fairness trade-offs across demographic groups, and transparency requirements for responsible deployment. Overall results show that ML models (particularly gradient boosting and hybrid ensembles) deliver higher predictive accuracy than logistic-regression baselines and raise approval rates for thin-file applicants without a proportional rise in default risk. However, improvements in access do not automatically translate into equitable outcomes; residual disparities remain, highlighting the need for fairness-aware governance. Explainability tools improve decision transparency but may exhibit instability under class imbalance and data drift that are common in thin-file portfolios. The paper concludes by proposing operational and policy guardrails—fairness audits, interpretable decision rationales, standardized adverse-action notices, and strict data-protection practices—to ensure that AI-based credit scoring advances inclusion while maintaining accountability and consumer trust.
Keywords	Alternative data, artificial intelligence, credit scoring, fairness, financial inclusion, machine learning, transparency
Field	Business Administration
Published In	Volume 6, Issue 6, November-December 2025
Published On	2025-11-28

View / Download PDF File

E-ISSN 3048-7641

doi

CrossRef DOI is assigned to each research paper published in our journal.

AIJFR DOI prefix is
10.63363/aijfr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About AIJFR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9898-79-39-59	editor@aijfr.com

Advanced International Journal for Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

AI-Driven Credit Scoring and Financial Inclusion: Performance, Fairness, And Transparency in Alternative-Data Lending

Share this