Signal · indexed from World Bank Documents & Reports
World Bank
This note examines whether automated loan screening can reduce gender disparities in SME lending, drawing on evidence from a pilot program implemented by a major commercial bank in Peru. The bank introduced a psychometric credit-scoring tool that automatically assessed loan applicants and determined approvals and loan sizes based on objective criteria, reducing the role of loan officer discretion. Using data from 1,883 SME applicants and a regression discontinuity design, the study finds that under traditional lending processes, women were less likely to take up loans and received significantly smaller loan amounts than men, despite similar approval rates. In contrast, these gender differences disappeared when loan decisions were based on the automated scoring system. The findings suggest that discretion in lending decisions contributed to unequal loan terms for women rather than differences in creditworthiness. Importantly, eliminating this discretion did not increase loan defaults, indicating that fairer lending practices can enhance financial inclusion without raising risk. The study highlights the potential of well-designed automated screening tools to reduce gender bias in access to finance while supporting sound lending outcomes.
Provenance
The notice above is the public record. Signing in adds the analysis: saved views and alerts on searches like this one, workflow and pipeline, exports and full workspace tooling.
| Field | How we know | State | Confidence |
|---|---|---|---|
| Publication date | Official API or feed | Data quality: Source-backed | 100 |
States describe GLODA's confidence in its own fields, never a judgement on the notice or its parties. Methodology