Zest’s software mitigates bias in credit underwriting algorithms so that banks, credit unions, and other lenders can lend more transparently and profitably without fear of violating fair lending and fair credit laws.
Zest AI uses a technique called adversarial debiasing to mitigate biases from its credit models. It pits a model trained on historical loan data against an algorithm trained to look for bias, forcing the original model to reduce or adjust the factors that lead to biased results. That could reduce the impact on the model of bias-generating credit variables such as credit history, which can often be a proxy for race.”
Our mission is to enable our partners in the highly regulated financial lending industries, deploy powerful and compliant machine learning models swiftly and easily; in order to better serve and identify dependable borrowers in their respective business.
Company Type: Startup
Region: US & Canada
Product: Zest AI Model Management System
Research: Resources & Whitepapers