Challenge
One major barrier to collecting and using GDD is existing data structures. What should you do if existing accounts were configured without a gender identifier? Certainly, one could add a gender identifier to every new account, but this would not allow you to analyze established users. You could also ask existing users to identify their gender, but this is impractical (particularly for dormant accounts) and introduces friction in the user experience. Even where gender information was collected during account sign-up but not associated with an account on the backend, manually associating this information would prove time-consuming and costly.
Standard Chartered identified a need to identify MSME bank accounts owned by women as part of its commitment to developing solutions tailored to women end-users globally.
Approach
The banks developed the Standard Chartered SocialAI Model, a tool that disaggregates the bank’s MSME portfolio by gender as part of the bank’s global commitment to advancing gender equity. [1]
Even when banks update systems to capture sex-disaggregated data for new clients, they often face the much larger hurdle of how to identify women-owned businesses in their existing portfolios.
“Where are the Women Entrepreneurs“, We-Fi
Results
The Standard Chartered SocialAI model, developed in 2023, can identify the gender with 90% accuracy by using customer names and information included in national ID numbers, where available, as inputs to a machine learning model. The bank has made the SocialAI model public so that other financial institutions can address the same challenge.
[1] Aurica Balmus, Evangeline Zhao, and Xu Jun, “Where are the Women Entrepreneurs? A Case Study on Standard Chartered’s SocialAI Model to Identify Women-Owned SMEs in Bank Portfolios,” We-Fi, accessed August 25, 2026, https://we-fi.org/scb-case-study/.