Machine Learning Underwriting Models & Cash-Flow Data

Overview

FinRegLab has conducted a ground-breaking comparison of using machine learning underwriting models with and without cash-flow data to increase responsible access to credit for consumers who may otherwise find it difficult to obtain safe and affordable loans.

Large banks and fintechs are increasingly working to improve their underwriting models by using machine learning techniques, alternative data sources such as bank transaction account records, or a combination of the two innovations.  However, no publicly available research directly compares each innovation’s separate and combined effects on the accuracy of underwriting models and on access to credit for consumers. The project builds on FinRegLab’s prior empirical analyses of alternative data and techniques for managing concerns about the explainability and fairness of machine learning underwriting models. The research findings can help to inform the broader lending ecosystem and may be particularly helpful to smaller institutions, advocates, and policymakers in prioritizing resources and new initiatives.