Prestige Deploys Zest Machine Learning Credit Model For Subprime Auto, Doubles Lending Volume

Bruce Upbin

September 27, 2018

Prestige Financial Services, like a lot of other subprime auto lenders, was dealing with rising borrower defaults at the end of 2016. It moved quickly to minimize the impact by tightening up lending. Suddenly, roughly seven out of ten applicants were being turned down for a loan.

Prestige wanted to know: “Is it possible to grow in a downturn without adding risk?” It is, by applying the better math and data science of machine learning to credit approvals. In early 2017 Prestige turned to Zest for help deploying a machine learning credit model. The Zest team was able to build and train a robust, new machine learning credit model in just three months, and put it into production shortly after—all using Zest Automated Machine Learning software tools. The model is fully explainable, too. “That was fast,” Warnick said. “We had never done that level of implementation or production in a cloud environment.”

In the months since deploying a ZAML credit model, Prestige’s lending volume has doubled, driven by a 36% increase in new applicants and a 14% increase in borrower approvals. Higher approval rates and more attractive pricing are driving current dealer-customers to send more business Prestige’s way, in addition to attracting new customers. The new loans underwritten on the Zest platform are performing at least as well as, if not better than, those Prestige had previously issued.

Thanks to its embrace of innovation, Prestige is meeting its original strategic goal to approve more borrowers without taking on more risk.

Read the entire case study here.

Thank you for subscribing!
Something went wrong while submitting the form.