This paper summarizes the machine learning project’s key empirical research findings and discusses the regulatory and public policy implications to be considered with the increasing use of machine learning models and explainability and fairness techniques.

This empirical white paper assesses the capabilities and limitations of available model diagnostic tools in helping lenders manage machine learning underwriting models. It focuses on the tools’ production of information relevant to adverse action, fair lending, and model risk management requirements.

FinRegLab is investigating the financial inclusion and consumer protection implications of using new data sources for credit underwriting of micro and small enterprises (MSEs) in Kenya with a particular focus on women-owned small businesses.

This report surveys the options that are available to consumers who are struggling with unsecured debt, including available research on the options’ scope and outcomes. It provides an overview of market and policy challenges as stakeholders ponder strategies to help consumers recover more quickly from personal and broader economic crises such as COVID-19.

This executive summary highlights key themes from our longer market and policy context report, which surveys the options available to consumers who are struggling with unsecured debt and market and policy challenges to helping consumers recover more quickly from financial shocks.

FinRegLab partnered with the Urban Institute to detail twenty years of research and efforts to access utility, telecom, and rental payment history for credit scoring and underwriting. The paper describes recent initiatives and key challenges going forward.

Utility, telecom, and rental payment history can help to assess how credit applicants manage housing and other recurring expenses. FinRegLab and the Urban Institute have examined available research, historical and recent initiatives to increase data access and use for credit underwriting, and market and policy issues that will determine whether such efforts can reach scale.

FinRegLab presented a research proposal for research on the use of federated machine learning in Bank Secrecy Act/Anti-Money laundering compliance to the Central Bank of the Future Conference, which was hosted by the Federal Reserve Bank of San Francisco and the University of Michigan’s Center on Finance, Law & Policy. The 2020 edition of this conference explored the changing role of central banks and their potential to foster more inclusive economies in the United States and around the world. We also convened a panel conversation to highlight the potential inclusion and efficiency benefits of using federated learning for BSA/AML.

This report surveys market practice with respect to the use of machine learning underwriting models and provides an overview of the current questions, debates, and regulatory frameworks that are shaping adoption and use.

This overview highlights key themes from our longer market & data science context report, including the state of machine learning adoption for credit underwriting and key issues in developing and managing machine learning models with regard to explainability and fairness.