Alternative Data and Ethical Lending Decisions for Underserved Borrowers

Samuel O. Adeyemi

Alternative Data and Ethical Lending Decisions for Underserved Borrowers

Author(s)	Dr. Samuel O. Adeyemi
Country	United States
Abstract	Limited or incomplete credit histories continue to constrain formal borrowing opportunities for individuals whose repayment capacity is inadequately represented by conventional credit-reporting systems. Alternative data offer a possible response by allowing lenders to consider additional signals such as cash-flow stability, rental and utility payments, payroll deposits, account balances, transaction regularity, and other permissioned financial information. However, expanding the volume of data used in underwriting does not automatically make lending more inclusive or ethical. Alternative variables may improve prediction while simultaneously introducing privacy concerns, opaque decision pathways, socioeconomic proxies, measurement errors, or new forms of algorithmic disadvantage. This study develops an ethical alternative-data lending framework for underserved borrowers by integrating financial-inclusion research, credit-risk modeling, algorithmic fairness, explainable artificial intelligence, data governance, and responsible lending principles. Because no primary borrower-level dataset was supplied, the quantitative component uses 500 synthetic loan-applicant profiles solely for methodological illustration. The simulation compares traditional credit scoring with alternative-data models and an ethically governed hybrid approach incorporating consent-based data selection, fairness monitoring, explainability, proportionality, and human review. Illustrative results suggest that appropriately selected alternative data can improve recognition of creditworthy thin-file applicants and reduce false-negative lending decisions. However, an unconstrained alternative-data model also produces greater fairness and transparency concerns. The ethically governed hybrid model provides the strongest balance between simulated inclusion, default control, decision explainability, and disparity reduction. The study argues that the central objective of alternative-data lending should not be maximum predictive extraction from personal information but proportionate improvement in creditworthiness assessment using relevant, explainable, and responsibly governed data. Alternative data can support financial inclusion only when lenders establish clear data-purpose boundaries, obtain meaningful permission where appropriate, monitor differential outcomes, provide understandable decision reasons, and maintain mechanisms for correction and human reconsideration.
Keywords	alternative data; ethical lending; underserved borrowers; credit scoring; financial inclusion; algorithmic fairness; explainable AI; cash-flow underwriting; responsible lending; fintech
Field	Engineering
Published In	Volume 1, Issue 5, September-October 2020
Published On	2020-10-08

View / Download PDF File

About AJAMIR 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		+1-872-302-3851	editor@ajamir.com

American Journal of Advanced Multidisciplinary Innovation and Research

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

Alternative Data and Ethical Lending Decisions for Underserved Borrowers

Share this