Elena Ionenko, co-founder and COO at TurnKey Lender, shares her insight into real-life applications of AI in lending in a new Forbes Council piece:
The traditional approach to loan-portfolio management puts collections and overall performance on one side, and origination on the other, with decisions that should be closely coordinated made by separate departments, often deployed across distinct software systems.
But that’s changing as senior managers work to strengthen ties between departments and advances in artificial intelligence allow for more nuanced — and more inclusive — procedures for vetting would-be borrowers.
Putting origination on an equal footing with other parts of loan management does more than provide holistic overviews. It puts extra resources into gatekeeping, providing a crucial first step in credit-risk evaluation and fraud detection, a must-have for overall portfolio health.
It also equips lenders to compete in today’s tough economic environment, a byproduct of business shutdowns, workplace furloughs and the general public’s hesitancy to congregate in a pandemic. In this context, it’s vital that alternative data inputs be uniformly formatted, easy to interpret, and available as an aid to decision making.
Converting such data into a scoring model requires advanced artificial-intelligence tools and processes, tons of historical data, and years of hands-on experience. But AI-derived credit scoring is vastly more accurate than traditional approaches — which hinge on credit-bureau scores and application responses — and provides lenders with the confidence they’re getting a fuller picture of applicants and approving better-performing loan, even in hard times.
The result? More good loans and better portfolio performance.
Meanwhile, there are real-world consequences to sticking with outmoded scoring models. Because old-line lenders aren’t usually able to change underwriting standards without accessing flexible, easy-to-configure and easy-to-deploy technology, it’s likely banks will experience a new wave of non-performing loans in the next year, according to industry consensus.