Abstract

Financial exclusion remains a persistent and structurally entrenched problem in the United States, with an estimated 26 million adults classified as 'credit invisible' and tens of millions more locked out of affordable credit by the limitations of traditional FICO-based scoring systems that fail to capture the financial realities of underserved populations. This study investigates how machine learning (ML) and predictive analytics frameworks, augmented with alternative data sources, can systematically expand credit accessibility for low-income, minority, rural, and immigrant communities that have historically been underrepresented in the formal financial system. Drawing on a comprehensive review of 56 empirical and theoretical studies published between 2015 and 2025, we examine the performance of diverse ML algorithms including random forests, gradient boosting, deep neural networks, and long short-term memory (LSTM) networks in credit scoring contexts, with particular attention to their differential impacts on financial inclusion outcomes. The paper analyzes the predictive validity of alternative data inputs such as rent and utility payment histories, mobile phone usage patterns, gig economy earnings, and bank transaction flows as substitutes for or supplements to conventional credit bureau data. We engage critically with the dual risks of algorithmic bias and privacy violation, which can inadvertently replicate or amplify existing patterns of discrimination when ML models are trained on historically biased data without appropriate fairness interventions. A comprehensive regulatory analysis situates our findings within the evolving legal framework governing algorithmic lending in the United States, including the Equal Credit Opportunity Act, the Fair Credit Reporting Act, and emerging CFPB guidance on explainable AI. Our synthesis reveals that well-designed ML-based credit scoring systems can increase approval rates for underserved populations by 20–45 percentage points while simultaneously reducing default rates, but that achieving these outcomes requires deliberate fairness engineering, robust model governance, and coordinated regulatory modernization. The paper concludes with a policy framework for responsible implementation of ML-driven credit scoring that prioritizes both financial inclusion and ethical accountability.

References

• Agarwal, S., Alok, S., Ghosh, P., & Gupta, S. (2020). Financial inclusion and alternate credit scoring for the millennials: Role of big data and machine learning in fintech. SSRN. https://doi.org/10.2139/ssrn.3507827
• Awaworyi-Churchill, S. (2019). Microfinance financial sustainability and outreach: Is there a trade-off? Empirical Economics, 59(3), 1329–1350.
• Bao, Z., & Huang, D. (2021). Shadow banking in a crisis: Evidence from Fintech during COVID-19. Journal of Financial and Quantitative Analysis, 56(7), 2320–2355.
• Bartlett, R., Morse, A., Stanton, R., & Wallace, N. (2022). Consumer lending discrimination in the fintech era. Journal of Financial Economics, 143(1), 30–56.
• Brown, J. R., Cookson, J. A., & Heimer, R. Z. (2019). Growing up without finance. Journal of Financial Economics, 134(3), 591–616.
• Bucker, M., Szepannek, G., Gosiewska, A., & Biecek, P. (2022). Transparency, auditability, and explainability of machine learning models in credit scoring. Journal of the Operational Research Society, 73(1), 70–90.
• Burtch, G., & Chan, J. (2019). Investigating the relationship between medical crowdfunding and personal bankruptcy in the United States. MIS Quarterly, 43(1), 237–262.
• Chen, Z., Liu, Y. J., Meng, J., & Wang, Z. (2023). What's in a face? An experiment on facial information and loan-approval decision. Management Science, 69(4), 2263–2283.
• Cowgill, B., Dell'Acqua, F., Deng, S., Hsu, D., Verma, N., & Chaintreau, A. (2020). Biased programmers? or biased data? A field experiment in operationalizing AI ethics. SSRN.
• Di Giuseppe, D. (2021). Credit scoring model using machine learning (Working paper). LUISS.
• Dobbie, W., Liberman, A., Paravisini, D., & Pathania, V. (2021). Measuring bias in consumer lending. The Review of Economic Studies, 88(6), 2799–2832.
• Dubber, M. D., Pasquale, F., & Das, S. (2020). The Oxford handbook of ethics of AI. Oxford University Press.
• Fu, R., Huang, Y., & Singh, P. V. (2021). Crowds, lending, machine, and Bias. Information Systems Research, 32(1), 72–92.
• Fügener, A., Grahl, J., Gupta, A., & Ketter, W. (2022). Cognitive challenges in human–artificial intelligence collaboration. Information Systems Research, 33(2), 678–696.
• Gao, H., Kumar, S., Tan, Y., & Zhao, H. (2022). Socialize more, pay less: Randomized field experiments on social pricing. Information Systems Research, 33(3), 935–953.
• Gianfrancesco, M. A., Tamang, S., Yazdany, J., & Schmajuk, G. (2018). Potential biases in machine learning algorithms using electronic health record data. JAMA Internal Medicine, 178(11), 1544.
• Gomber, P., Kauffman, R. J., Parker, C., & Weber, B. W. (2018). On the Fintech revolution. Journal of Management Information Systems, 35(1), 220–265.
• Gopal, R. D., Hidaji, H., Kutlu, S. N., Patterson, R. A., & Yaraghi, N. (2023). Law, economics, and privacy. Information Systems Research, 34(4), 1375–1397.
• Gunnarsson, B. R., vanden Broucke, S., Baesens, B., Óskarsdóttir, M., & Lemahieu, W. (2021). Deep learning for credit scoring: Do or don't? European Journal of Operational Research, 295(1), 292–305.
• Guo, Y., Zhou, W., Luo, C., Liu, C., & Xiong, H. (2015). Instance-based credit risk assessment for investment decisions in P2P lending. European Journal of Operational Research, 249(2), 417–426.
• Hao, K., & Stray, J. (2019). Can you make AI fairer than a judge? MIT Technology Review.
• Hiller, J. S. (2020). Fairness in the eyes of the beholder: AI, fairness, and alternative credit scoring. West Virginia Law Review, 123(3), 907–935.
• Hurlin, C., Perignon, C., & Saurin, S. (2022). The fairness of credit scoring models. SSRN.
• Jagtiani, J., & Lemieux, C. (2019). The roles of alternative data and machine learning in fintech lending. Financial Management, 48(4), 1009–1029.
• Johnson, K. N. (2019). Examining the use of alternative data in underwriting and credit scoring to expand access to credit. SSRN.
• Kallus, N., Mao, X., & Zhou, A. (2020). Assessing algorithmic fairness with unobserved protected class using data combination. ACM FAccT.
• Kankanhalli, A., Charalabidis, Y., & Mellouli, S. (2019). IoT and AI for smart government: A research agenda. Government Information Quarterly, 36(2), 304–309.
• Katebi, A., Homami, P., & Najmeddin, M. (2022). Acceptance model of precast concrete components based on TAM and TOE framework. Journal of Building Engineering, 45, 103518.
• Kim, D. (2019). The importance of detailed patterns of herding behaviour in a P2P lending market. Applied Economics Letters, 27(2), 127–130.
• Kshetri, N. (2021). The role of artificial intelligence in promoting financial inclusion in developing countries. Journal of Global Information Technology Management, 24(1), 1–6.
• Kwon, J., & Johnson, M. (2018). Meaningful healthcare security: Does meaningful-use attestation improve information security performance? MIS Quarterly, 42(4), 1043–1067.
• Langenbucher, K. (2020). Responsible AI-based credit scoring: A legal framework. European Business Law Review, 31(4), 527–572.
• Laouénan, M., & Rathelot, R. (2022). Can information reduce ethnic discrimination? American Economic Journal: Applied Economics, 14(1), 107–132.
• Li, C., Wang, H., Jiang, S., & Gu, B. (2024). The effect of AI-enabled credit scoring on financial inclusion: Evidence from an underserved population of over one million. MIS Quarterly, 48(4), 1803–1834.
• Li, J., & Hu, J. (2019). Does university reputation matter? Evidence from peer-to-peer lending. Finance Research Letters, 31, 66–77.
• Liang, F., Das, V., Kostyuk, N., & Hussain, M. M. (2018). Constructing a data-driven society: China's social credit system. Policy & Internet, 10(4), 415–453.
• Liberti, J. M. (2018). Initiative, incentives, and soft information. Management Science, 64(8), 3714–3734.
• Liberti, J. M., & Petersen, M. A. (2019). Information: Hard and soft. Review of Corporate Finance Studies, 8(1), 1–41.
• Liu, M. (2022). Assessing human information processing in lending decisions: A machine learning approach. Journal of Accounting Research, 60(2), 607–651.
• Loufield, E., Ferenzy, D., & Johnson, T. (2018). Accelerating financial inclusion with new data. Center for Financial Inclusion.
• Lu, J., Lee, D., Kim, T. W., & Danks, D. (2019). Good explanation for algorithmic transparency. SSRN.
• Lu, T., Zhang, Y., & Li, B. (2023). Profit vs. equality? The case of financial risk assessment and alternative data. MIS Quarterly, 47(4), 1517–1556.
• Ma, L., Zhao, X., Zhou, Z., & Liu, Y. (2018). A new aspect on P2P online lending default prediction using meta-level phone usage data in China. Decision Support Systems, 111, 60–71.
• Macha, M., Foutz, N., Li, B., & Ghose, A. (2023). Personalized privacy preservation in consumer mobile trajectories. Information Systems Research, 35(1), 249–271.
• Martin, K. (2019). Designing ethical algorithms. MIS Quarterly Executive, 18(2), 129–142.
• Neumann, N., Tucker, C. E., Kaplan, L., Mislove, A., & Sapiezynski, P. (in press). Data deserts and black box bias. Management Science.
• Nowak, A., Ross, A., & Yencha, C. (2018). Small business borrowing and peer-to-peer lending. Contemporary Economic Policy, 36(2), 318–336.
• Nwaimo, A., Adegbola, O., & Adegbola, P. (2024). Predictive analytics for financial inclusion: Using machine learning to improve credit access for underbanked populations. Computer Science & IT Research Journal, 5(6), 1358–1373.
• O'Neil, C. (2017). Weapons of math destruction. Crown.
• Rudin, C. (2019). Stop explaining black box machine learning models for high stakes decisions. Nature Machine Intelligence, 1(5), 206–215.
• Sabeena, A. A., Ahmed, A., Sharmin, S., & Hassan, A. (2025). Using alternative data and machine learning for predictive credit scoring to promote financial inclusion in the U.S. ResearchGate.
• Serrano-Cinca, C., & Gutiérrez-Nieto, B. (2016). The use of profit scoring as an alternative to credit scoring in P2P lending. Decision Support Systems, 89, 113–122.