Something I noted from the press release this morning:
“For 2020, Upstart’s model approved 30% more Black borrowers than a traditional model and provided 11% lower interest rates than a traditional model.”
But I recall from a previous UPST blog post:
“2019 results showed that Upstart’s model increased approval rates for African-American applicants by more than 45% with 21% lower APRs compared to a traditional credit model.” https://www.upstart.com/blog/why-i-joined-upstart
I wonder if part of the reason for the decrease is due to “forced” changes thanks to mislead claims by SBPC last year and congress jumping on that bandwagon.
That led to the whole Relman Colfax report in April 2021 (by the way they have given no update last month, even though they said they would for October).
All my speculation though. But interesting.
Here were the changes implemented, per Relman Colfax:
https://www.relmanlaw.com/media/cases/1088_Upstart%20Initial…
“In responses to those conversations, as well as the congressional inquiry, Upstart made certain changes to how its underwriting model utilized educational data. Most notably, it abolished the use of average incoming SAT and ACT scores to group education institutions in its underwriting model. While Upstart’s model continues to incorporate information about the educational institution attended, it switched to grouping schools based on average post- graduation income. Upstart also established a “normalization” process for “Minority Serving Institutions” (“MSIs”)—which Upstart defines as schools where 80 percent or more of the student body are members of the same racial demographic group.103 Under that process, Upstart normalized MSIs as a group to have equal graduate incomes as non-MSIs by calculating and using the distance, as a percentage, between a school’s graduate incomes and its respective school group average (i.e., MSIs, non-MSIs). This process results in MSIs and non-MSIs being on average equal. Put another way, above average MSIs (in terms of graduate income) are treated above average overall by as much as they are above the MSI average. Any decisioning, including tranching, is then performed on this normalized information.”