Reproducibility package for Does Automatic Loan Approval Reduce Gender Bias In SME Lending?
Overview
This paper examines whether automatic credit approval can reduce gender bias in SME lending. We collaborated with a bank in Peru that piloted a new screening tool to generate psychometric credit scores. Applicants who scored above a predefined threshold were automatically offered a loan with a size tied to their score, while those below the threshold were assessed by a loan officer. Using a regression discontinuity design and credit bureau data, we compare loan offers and loan sizes of female and male applicants within a narrow window around the automatic approval threshold. The results show that female applicants below the threshold are less likely to take out loans and receive smaller loan amounts than men. However, this gender bias disappears for applicants above the threshold, suggesting that automated screening methods can reduce loan officer discretion and promote gender equity in lending.
Reproducibility Package
| Repository name | URI |
|---|---|
| Reproducible Research Repository (World Bank) | https://reproducibility.worldbank.org |
Reproducibility
Paper exhibits were reproduced on a computer with the following specifications:
• OS: Windows 11 Enterprise
• Processor: Intel(R) Xeon(R) Gold 6226R CPU @ 2.90GHz
• Memory available: 16.0 GB
Runtime: 30 minutes
Since all data used in the analysis are restricted, the reproducibility review was conducted through virtual verification following the Virtual Reproducibility Verification Protocols.
To reproduce the findings in this paper, a user must:
- Obtain access to the restricted data: The data used in this paper are restricted and require special permissions.
- Adjust file paths and run the code: Update the directory specified in line 1 of
master.doand run the script. All outputs will be generated in theoutputfolder.
Because access to the restricted data may not be possible for most users, this package includes the outputs generated by the author and verified by the reviewers. These files can be used to review and validate the results presented in the paper.
Data
All data is restricted and has not been included in the reproducibility package. For more details, please refer to the README file.
Description
| Author | Affiliation | |
|---|---|---|
| Claudia Ruiz Ortega | DECRG | cruizortega@worldbank.org |
| Irani Arraiz | IDB Invest | IARRAIZ@iadb.org |
| Miriam Bruhn | DECRG World Bank | mbruhn@worldbank.org |
2026-03-31
Scope and coverage
| Location | Code |
|---|---|
| Peru | PER |
Disclaimer
The materials in the reproducibility packages are distributed as they were prepared by the staff of the International Bank for Reconstruction and Development/The World Bank. The findings, interpretations, and conclusions expressed in this event do not necessarily reflect the views of the World Bank, the Executive Directors of the World Bank, or the governments they represent. The World Bank does not guarantee the accuracy of the materials included in the reproducibility package.
Access and rights
| Name | URI |
|---|---|
| Modified BSD3 | https://opensource.org/license/bsd-3-clause/ |
Contacts
| Name | Affiliation | |
|---|---|---|
| Claudia Ruiz Ortega | DECRG | cruizortega@worldbank.org |
| Reproducibility WBG | World Bank | reproducibility@worldbank.org |
Information on metadata
| Name | Abbreviation | Affiliation | Role |
|---|---|---|---|
| Reproducibility WBG | DECDI | World Bank - Development Impact Department | Verification and preparation of metadata |
2026-03-31
1