AI-Driven Credit Scoring in Microfinance: Enhancing Financial Inclusion for SDG 5 and SDG 10
Arun Khatri et al.
What the paper says
AI-based credit scoring is progressively transforming microfinance by facilitating more inclusive, data-driven, and fair lending by focusing particularly on Sustainable Development Goals (SDG) 5 on Gender Equality and SDG 10 on Reduced Inequalities. Conventional ways of evaluating credit tend to lock out women, informal employees, and marginalized individuals based on limited collateral, skimpy credit report, and human prejudice. The author of this paper discusses the role of artificial intelligence methods like machine learning, alternative data analytics, and explainable artificial intelligence in promoting credit access and minimizing systemic discrimination in microfinance systems. The research design is mixed-methods with the combination of quantitative research on AI-based credit models and qualitative research on the results of borrower inclusion. Accuracy, default prediction, and reduction of bias are used to measure model performance whereas inclusion impact is measured based on the rates of gender participation, equity in loan approval and income mobility measures. The comparative analysis of AI-based credit scoring shows that it enhances by 29.4 percent the rate of loan approval by women borrowers and by 24.1 percent the rate of error due to income-based exclusions in comparison to rule-based systems. This is because the predictability of default risk is enhanced by 18.6 per cent without necessarily piling interest pressure on the at-risk borrowers. The results reveal that financial inclusion can be increased and responsible lending facilitated with the help of transparent and fairness sensitive AI models. With the potential to facilitate gender-inclusive entrepreneurship and decrease structural credit inequalities, AI-driven credit scoring becomes an important facilitator of inclusive economic behaviour, social fairness, and sustainable microfinance development in line with SDG 5 and SDG 10 in all developing economies in the world.
Evidence weight
Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40
| F · citation impact | 0.50 × 0.4 = 0.20 |
| M · momentum | 0.50 × 0.15 = 0.07 |
| V · venue signal | 0.50 × 0.05 = 0.03 |
| R · text relevance † | 0.50 × 0.4 = 0.20 |
† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.