Industry Report

One Year Later: 

AI Underwriting & Portfolio Performance Through COVID

How consumer loans originated before the pandemic performed through a year of economic uncertainty

Written by Jeff Keltner, SVP Business Development


One year after the peak of COVID-related portfolio stress, we can now look back and answer a key question: How did AI-enabled underwriting models perform in a time of uncertainty?

Leaders in financial services recognize the potential of artificial intelligence (AI) to transform underwriting and fraud detection — and a full year of data from 2020 is now here.

Discover the facts, figures, and charts that compare AI vs. traditional lending models.

One Year Later

DOWNLOAD YOUR FREE COPY

Deep dive into the data and learn how:


1

Impairment across AI-based loans increased 40% less than the industry as a whole


2

An AI model's "Risk Tier" was 6 times more effective than credit score bands at separating the risk of payment impairment


3

Fewer borrowers with AI enabled loans required a hardship program, and more of these borrowers began promptly making on-time payments


4

An AI model's separated risk tiers translated into significantly lower payment impairment rates for bank and credit union partners

Visit the Digital Lending Knowledge Hub for more resources like this one

Upstart Digital Lending Knowledge Hub