“The future is already here,” said sci-fi master William Gibson. “It's just not very evenly distributed.”
Same goes for the future of lending. As The Wall Street Journal reported, a growing number of lenders including Synchrony Financial, Ford Motor Credit Co., and Prestige Financial Services, "have looked into the future and believe it could include artificial intelligence as a tool to take increasing amounts of data and find relationships between variables to help determine creditworthiness."
These ZestFinance customers shared with the WSJ their take on the promise of machine learning and what it can do for their lending practices. Prestige, an auto lender owned by the same group that controls the NBA's Utah Jazz, was wrestling with how to boost business while maintaining underwriting standards in a tough subprime auto market. Working with Zest, Prestige's modelers started drilling down into some 2,700 borrower characteristics instead of the couple dozen that the lender typically had on its risk-assessment scorecard.
The work of developing new machine-learning models yielded some fresh insights. Bankruptcy, for example, was always a crucial signal for creditworthiness. But, as the WSJ wrote, "the timing of a bankruptcy is important because individuals are restricted from repeatedly trying to wipe out their debts. So someone fresh out of bankruptcy for the first time might be a better credit risk than someone who filed, say, six years ago." Instead of looking simply at whether a potential borrower has ever filed for bankruptcy, for example, Prestige's new machine-learning model considered such factors as when the bankruptcy happened and analyzed that data with other variables, including previous car-payment records and time spent living in his or her current residence.
Prestige saw a boost in business almost immediately after implementing its ML credit model. The lender’s volume in September 2018 was $55 million, more than double the amount from August 2017 during the tightest credit conditions. The new loans perform as well as those made under the old system.
Read the full story here, no paywall registration required.