Fair and Transparent Credit Risk Scoring for Consumers and Small Businesses Using Behavioral and Alternative Data to Support Responsible Lending and Economic Inclusion

Authors

  • Masrul Hasan*, Kazi Rakib Hasan Saurav, Md. Arifur Rahman

DOI:

https://doi.org/10.64882/ijrt.v13.i4.1900

Keywords:

credit risk, alternative data, explainable AI, fair lending, small business, economic inclusion, responsible lending, model risk management, 2025

Abstract

This study develops and evaluates a unified responsible-lending framework for consumer and small-business credit risk scoring using 2025 U.S. financial conditions, behavioral indicators, and alternative data. The framework combines conventional capacity and repayment variables with rent-payment consistency, transaction cash-flow margins, income volatility, payroll regularity, digital-sales activity, and trade-payment behavior. It is designed to improve predictive accuracy for thin-file applicants while preserving transparency, adverse-action specificity, and measurable fairness across applicant groups. The empirical context is anchored to verified 2025 national evidence: U.S. household debt reached $18.8 trillion at year-end, credit-card balances reached $1.28 trillion, 4.8 percent of outstanding debt was in some stage of delinquency, and the Small Business Administration guaranteed approximately 85,000 7(a) and 504 loans totaling $45 billion. Applicant-level model experiments use a reproducible 2025-calibrated analytical panel because no single public 2025 dataset combines complete credit outcomes, cash-flow features, small-business operating data, and protected-class information required for simultaneous accuracy and fairness evaluation. Results show that behavioral and alternative variables improve rank ordering and precision-recall performance, particularly for thin-file consumers and younger firms. However, predictive uplift is not treated as sufficient evidence for deployment. The proposed governance process requires proxy screening, less-discriminatory-alternative testing, subgroup calibration, reason-code validation, capacity-aware thresholds, human review, drift surveillance, and documented remediation. The paper contributes an integrated technical and operational blueprint for lenders seeking to expand access to credit without weakening model governance or fair-lending controls.

References

U.S. Small Business Administration. 7(a) and 504 Activity Reports: FY2025 Year End. SBA Open Data, 2025.

Consumer Financial Protection Bureau. Fair Lending Report of the Consumer Financial Protection Bureau. December 2025.

Consumer Financial Protection Bureau. Circular 2023-03: Adverse Action Notification Requirements and the Proper Use of CFPB Sample Forms.

Equal Credit Opportunity Act, 15 U.S.C. §§ 1691-1691f.

Regulation B, 12 C.F.R. Part 1002.

Fair Credit Reporting Act, 15 U.S.C. § 1681 et seq.

Federal Reserve Board and Office of the Comptroller of the Currency. Supervisory Guidance on Model Risk Management, SR 11-7 / OCC 2011-12.

National Institute of Standards and Technology. Artificial Intelligence Risk Management Framework (AI RMF 1.0). 2023.

Barocas, S., Hardt, M., and Narayanan, A. Fairness and Machine Learning. 2023.

Hardt, M., Price, E., and Srebro, N. Equality of Opportunity in Supervised Learning. NeurIPS, 2016.

Kleinberg, J., Mullainathan, S., and Raghavan, M. Inherent Trade-Offs in the Fair Determination of Risk Scores. 2016.

Chouldechova, A. Fair Prediction with Disparate Impact: A Study of Bias in Recidivism Prediction Instruments. Big Data, 2017.

Lundberg, S. M., and Lee, S. I. A Unified Approach to Interpreting Model Predictions. NeurIPS, 2017.

Ribeiro, M. T., Singh, S., and Guestrin, C. Why Should I Trust You? Explaining the Predictions of Any Classifier. KDD, 2016.

Hand, D. J., and Henley, W. E. Statistical Classification Methods in Consumer Credit Scoring. Journal of the Royal Statistical Society, 1997.

Thomas, L. C., Edelman, D. B., and Crook, J. N. Credit Scoring and Its Applications. SIAM, 2017.

Lessmann, S., Baesens, B., Seow, H. V., and Thomas, L. C. Benchmarking State-of-the-Art Classification Algorithms for Credit Scoring. European Journal of Operational Research, 2015.

Khandani, A. E., Kim, A. J., and Lo, A. W. Consumer Credit-Risk Models via Machine-Learning Algorithms. Journal of Banking & Finance, 2010.

Federal Reserve Board. Report to Congress on the Use of Alternative Data in Credit Underwriting. 2019.

Financial Stability Board. The Use of Supervisory and Regulatory Technology by Authorities and Regulated Institutions. 2020.

Basel Committee on Banking Supervision. Principles for the Management of Credit Risk. Bank for International Settlements.

Consumer Financial Protection Bureau. Small Business Lending Data Collection Rulemaking Materials, 2025.

Federal Financial Institutions Examination Council. Interagency Fair Lending Examination Procedures.

Office of the Comptroller of the Currency. Comptroller’s Handbook: Fair Lending.

U.S. Department of Justice. Equal Credit Opportunity Act Enforcement Materials.

Federal Trade Commission. Understanding Your Credit and Consumer Reporting Rights.

World Bank. Credit Reporting Knowledge Guide. International Finance Corporation.

Downloads

How to Cite

Masrul Hasan*, Kazi Rakib Hasan Saurav, Md. Arifur Rahman. (2025). Fair and Transparent Credit Risk Scoring for Consumers and Small Businesses Using Behavioral and Alternative Data to Support Responsible Lending and Economic Inclusion. International Journal of Research & Technology, 13(4), 1418–1440. https://doi.org/10.64882/ijrt.v13.i4.1900