A Machine Learning Perspective on FinTech-Driven Inclusion: Addressing Algorithm Bias in Credit Scoring Systems in Developing Economies

Abstract

The present paper is research on whether machine learning-supported FinTech innovations can be used to promote financial inclusion where access to credit is fair and reasonable to everyone in the emerging economies. It is also directly related to the issue of algorithmic bias in automated credit score systems that may block marginalized groups of individuals from accessing financial services (Agboola, 2025; Nwafor, Nwafor, and Brahma, 2024; Oguntibeju, 2024). It was a quantitative research design, and structured questionnaires were sent to 400 respondents both in the city and rural areas in the developing countries (Kothandapani, 2022; Sadok, Sakka, and El Maknouzi, 2022; Herrmann and Masawi, 2022). The main constructs that identified the adoption of FinTech and perceived algorithmic trust were identified through the PCA. Confirmatory Factor Analysis (CFA) and Structural Equation Modeling (SEM) were used to verify the correlation of variables such as educational background, gender inclusiveness, digital literacy, and perceived algorithmic fairness (Dumitrescu et al., 2022; Chen, Calabrese, and Martin-Barraga, 2024; Moscato, Picariello, and Sperli, 2021). It was possible due to Composite Reliability (CR), Average Variance Extraction (AVE), and several model-fit indicators (Bari, 2024; Fuster et al., 2021; Khandani, Kim, and Lo, 2010). We show that the level of education and gender-balanced leadership melting can have a positive impact on the creation of trust and acceptance towards ML-based credit systems, and there are inequalities in the emergence of algorithmic bias and the lack of transparency (Memarian, 2023; Bello, 2023; Gambacorta et al., 2024). It was also noted that perceived unfairness with the algorithms could be mediated by relying on the digital literacy and education that proved to be of the utmost importance in assisting in integrating inclusive finance (Zahir, Tonmoy, and Md Arifur, 2023; Abdullah Al et al., 2022; Md Masud, 2022). These results support the fact that these variables are mutually dependent and that the use of AI and inclusive policies is necessary to promote the sustainable realization of financial inclusion (Salami et al., 2025; Berg et al., 2019; Fuster et al., 2021). Regulatory interventions to support the creation of digital literacy, gender equality, and data algorithm responsibility should be coupled with technological innovation, which is not an inclusive development guarantee, but rather a supplement (Jagtiani and Lemieux, 2019; Herrmann and Masawi, 2022; Agboola, 2025).

Introduction

The text examines how FinTech credit scoring powered by machine learning (ML) is transforming financial inclusion but also creating serious concerns around algorithmic bias, fairness, and ethics—especially in developing economies.

FinTech systems help expand credit access for unbanked populations by using alternative data (mobile usage, transactions, e-commerce history), but these same systems can unintentionally reinforce inequality. Bias in training data, lack of transparency, and weak regulation often lead to unfair credit decisions that disadvantage women, rural users, low-income groups, and people with limited digital footprints.

The literature shows that:

• ML credit scoring improves access and prediction accuracy compared to traditional models.
• However, it frequently produces discriminatory outcomes due to unbalanced datasets and structural inequality.
• Fairness techniques (like reweighing and adversarial debiasing) can reduce bias but may slightly reduce accuracy.
• Many systems remain “black boxes,” limiting explainability and trust.
• Regulatory and governance gaps in developing countries worsen the problem.

The study highlights major research gaps, including:

• Lack of empirical studies in developing economies
• Weak integration of fairness metrics with socio-economic factors (gender, education, digital literacy)
• Limited real-world testing of fairness-aware ML systems in FinTech

To explain these issues, the paper uses four theoretical frameworks:

• Algorithmic Fairness Theory (core lens for bias and equity in ML decisions)
• Financial Inclusion Theory (focus on equitable access to finance)
• Technology Acceptance Model (trust and adoption of FinTech systems)
• Human Capital & Institutional Theory (role of education, governance, and social structures)

Key definitions clarify concepts like FinTech, algorithmic bias, credit scoring, financial inclusion, and ML fairness.

Conclusion

The present paper has been a review of convergence of algorithmic fairness, perceived trust, explainability, and financial inclusion within the dynamically evolving FinTech credit ecosystem. The research synthesized four theoretical frameworks, that is, the Algorithmic Fairness Theory, the Financial Inclusion Theory, the Technology Acceptance Model (TAM), and the Human Capital and Institutional Theory, as a way of giving a comprehensive understanding of how ethical and technological variables converge to establish the definition of inclusive financial outcomes. They discovered that perceived trust is substantially reinforced by applying algorithmic fairness and explainability, which results in financial inclusion that makes trust one of the critical mediating variables in AI-based credit systems. As noted in the paper, fairness and transparency are not only ethical requirements but also functional requirements to make FinTech adoption sustainable. Digital and economic inclusion through the creation of ethical machine learning models and their administration can also be enhanced through granting access to credit to underserved populations. Conversely, possessing bias and lack of understanding, these systems might go on to help generate structural inequalities, thereby undermining user trust and institutional credibility.

References

[1] Zahir, B., Tonmoy, B., & Md Arifur, R. (2023). UX optimization in digital workplace solutions: AI tools for remote support and user engagement in hybrid environments. International Journal of Scientific Interdisciplinary Research, 4(1), 27-51. https://doi.org/10.63125/33gqpx45 [2] Abdullah Al, M., Rajesh, P., Mohammad Hasan, I., & Zahir, B. (2022). A Systematic Review of The Role Of SQL And Excel In Data-Driven Business Decision-Making For Aspiring Analysts. American Journal of Scholarly Research and Innovation, 1(01), 249-269. https://doi.org/10.63125/n142cg62 [3] Md Masud, K. (2022). A Systematic Review Of Credit Risk Assessment Models In Emerging Economies: A Focus On Bangladesh\'s Commercial Banking Sector. American Journal of Advanced Technology and Engineering Solutions, 2(01), 01-31. https://doi.org/10.63125/p7ym0327 [4] Agboola, O. K. (2025). Auditing Bias in AI and Machine Learning-Based Credit Algorithms: A Data Science Perspective on Fairness and Ethics in FinTech. International Journal of Technology, Management and Humanities, 11(02), 1-11. DOI: 10.21590/ijtmh.11.02.10 [5] Kothandapani, H. P. (2022). Leveraging AI for credit scoring and financial inclusion in emerging markets. World Journal of Advanced Research and Reviews, 15(3), 526-539. https://doi.org/10.30574/wjarr.2022.15.3.0904 [6] Moscato, V., Picariello, A., & Sperlí, G. (2021). A benchmark of machine learning approaches for credit score prediction. Expert Systems with Applications, 165, 113986. https://doi.org/10.1016/j.eswa.2020.113986 [7] Sadok, H., Sakka, F., & El Maknouzi, M. E. H. (2022). Artificial intelligence and bank credit analysis: A review. Cogent Economics & Finance, 10(1). https://doi.org/10.1080/23322039.2021.2023262 [8] Memarian, B. (2023). Fairness, Accountability, Transparency, and Ethics (FATE) in Artificial Intelligence (AI) and higher education: A systematic review. Computers and Education: Artificial Intelligence, 5, 100152. https://doi.org/10.1016/j.caeai.2023.100152 [9] Herrmann, H., & Masawi, B. (2022). Three and a half decades of artificial intelligence in banking, financial services, and insurance: A systematic evolutionary review. Strategic Change. https://doi.org/10.1002/jsc.2525 [10] Khandani, A. E., Kim, A. J., & Lo, A. W. (2010). Consumer Credit-Risk Models Via Machine-Learning Algorithms. Journal of Banking & Finance, 34(11), 2767-2787. https://doi.org/10.1016/j.jbankfin.2010.06.001 [11] Jagtiani, J., & Lemieux, C. (2019). The roles of alternative data and machine learning in fintech lending: Evidence from the Lending Club consumer platform. Financial Management, 48(4), https://doi.org/10.1111/fima.12295 [12] Hertzberg, A., Liberman, A., & Paravisini, D. (2018). Screening on Loan Terms: Evidence from Maturity Choice in Consumer Credit. The Review of Financial Studies, 31(9), https://doi.org/10.1093/rfs/hhy024 [13] Gambacorta, L., Huang, Y., Qiu, H., & Wang, J. (2024). How do machine learning and non-traditional data affect credit scoring? New evidence from a Chinese fintech firm. Journal of Financial Stability, 73, 101284. https://doi.org/10.1016/j.jfs.2024.101 284 [14] Berg, T., Burg, V., Gombovi?, A., & Puri, M. (2019). On the Rise of FinTechs: Credit Scoring Using Digital Footprints. The Review of Financial Studies, 33(7), 2845-2897. https://doi.org/10.1093/rfs/hhz099 [15] Fuster, A., Goldsmith-Pinkham, P., Ramadorai, T., & Walther, A. (2021). Predictably Unequal? The Effects of Machine Learning on Credit Markets. The Journal of Finance, 77(1), https://doi.org/10.1111/jofi.13090 [16] Iyer, R., Khwaja, A. I., Luttmer, E. F. P., & Shue, K. (2016). Screening Peers Softly: Inferring the Quality of Small Borrowers. Management Science, 62(6), 1554-1577. https://doi.org/10.1287/mnsc.2015.2181 [17] Bello, O. A. (2023). Machine learning algorithms for credit risk assessment: an economic and financial analysis. International Journal of Management, 10(1), 109-133. https://doi.org/10.37745/ijmt.2013/vol10n1109133 [18] Effectiveness and Impact of Fintech Credit Scoring Models on Financial Inclusion 46 https://doi.org/10.13140/RG.2.2.23780.04480 [19] Oguntibeju, O. O. (2024). Mitigating artificial intelligence bias in financial systems: A comparative analysis of debiasing techniques. Asian Journal of Research in Computer Science, 17(12), 165-178. https://doi.org/10.9734/ajrcos/2024/v17i12536 [20] Salami, I. A., Adesokan-Imran, T. O., Tiwo, O. J., Metibemu, O. C., Olutimehin, A. T., & Olaniyi, O. O. (2025). Addressing bias and data privacy concerns in AI-driven credit scoring systems through cybersecurity risk assessment. Asian Journal of Research in Computer Science, 18(4), 59-82. https://doi.org/10.9734/ajrcos/2025/v18i4608 [21] Nwafor, C. N., Nwafor, O., & Brahma, S. (2024). Enhancing transparency and fairness in automated credit decisions: an explainable novel hybrid machine learning approach. Scientific Reports, 14(1), 25174. https://doi.org/10.1038/s41598-024-750268 [22] Bari, M. H. (2024). A systematic literature review of predictive models and analytics in ai-driven credit scoring. Available at SSRN 5050068. https://dx.doi.org/10.2139/ssrn.5050068 [23] Chen, Y., Calabrese, R., & Martin-Barragan, B. (2024). Interpretable machine learning for imbalanced credit scoring datasets. European Journal of Operational Research, 312(1), 357-372.https://doi.org/10.1016/j.ejor.2023.06.036 [24] Financing by Logistic Regression, Artificial Neural Network and Hybrid Models. Sustainability, 8(5), 433-NA. https://doi.org/10.3390/su8050433 [25] Dumitrescu, E., Hué, S., Hurlin, C., & Tokpavi, S. (2022). Machine learning for credit scoring: Improving logistic regression with non-linear decision-tree effects. European Journal of Operational Research, 297(3), 1178-1192. https://doi.org/10.1016/j.ejor.2021.06.053

Copyright

Copyright © 2026 Dr. T. Kishore Kumar, Tasneem Saba, Bidisha Sewa, Gursimran Kaur, Priyanka Kumari. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.