CHALLENGE - Combat rising defaults - Reduce portfolio risk without sacrificing approvals - $1.1 Billion Assets - Specialty Auto Lender - New to machine learning 3 MONTH production time 33% reduction in credit losses 100% increase in lending volume 14% increase in approvals RESULTS Prestige engaged Zest when Michael Francis, a junior risk analyst, proposed using machine learning to help combat rising defaults without sacrificing approvals. With only a handful of risk analysts, they just did not have the technical expertise and resources to build and train a model quickly. Building a Better Model, Quickly T o start, Zest analysts compiled the necessary data—historical loan performance data, credit bureau data, and alternative scoring statistics that Prestige had relied

Join for free to read