When you apply for a loan, most lenders will check your credit score and verify your income. But no Upstart Holdings (NASDAQ: UPST). The company uses more than 1,000 data points in its artificial intelligence-based process to make smarter lending decisions. In this Fool live Video clip, recorded on April 5, Fool.com Contributor Matt Frankel, CFP, and Focus on industry Host Jason Moser discusses Upstart’s unique approach and why it is such an important competitive advantage.

10 stocks we love better than Upstart Holdings, Inc.
When investment geniuses David and Tom Gardner have stock advice, he can pay to listen. After all, the newsletter they’ve been distributing for over a decade, Motley Fool Fellowship Advisor, has tripled the market. *

David and Tom just revealed what they think are the ten best stocks investors can buy right now … and Upstart Holdings, Inc. was not one of them! That’s right – they think these 10 stocks are even better buys.

See the 10 actions

* Stock Advisor returns as of February 24, 2021

Matthew Frankel: Alright, so the most voted question is from Disk which says, “What are some of the data points that Upstart looks at the only ones they have access to, and how do they get that data?” Obviously, a lot of it is proprietary. They’re not going to give away their secret sauce. But the point is that if, for example, a borrower who applies for a credit card in default five years ago, his salary has increased by X amount per year since then, he has two credit cards that ‘he paid with a fine, things like that. Considering this combination, what is the probability of default on a car loan or personal loan? This is the question Upstart tries to answer. Most lenders simply look at the borrower’s FICO score and perhaps their income to see if they can afford the loan. These are data points like auto loan history, past repossessions, or how long has their last overdue credit card payment been? A bunch of different personal data points. Do they have a bachelor’s degree? Is not it? This is a big problem that a lot of these fintechs use that correlates with payment history.

Jason Moser: Yes.

Frankel: As they build their database, if they make a million loans, they have that data for a million different clients and can really see the correlation between some variables that other lenders can’t quite get. simply not. They are not the only ones who have access to its data. Obviously, any lender can ask a borrower if they have a bachelor’s degree, for example. It’s just a matter of creating a big library of that data and using it in combination with all of these other variables to see the correlations that other lenders can’t.

Moser: Yes, I know I’ve used this example before, but Xoom, the money transfer company that Pay Pal (NASDAQ: PYPL) acquired some time ago, that’s what they did very well, that they put this risk assessment model in place, and it was able to just incorporate a lot of data points that they have learned from the transactions, the people who do business with them, they were able to get information on a million different data points and then turn that into a risk assessment model to basically determine if anyone send this money, is it good for it? Are we going to have a situation where we either have fraud or accounts that are not payable? They were really able to take that and minimize the losses. It shows again that it was this idea of ​​taking the data, it’s like you get the data, that’s one thing, but then knowing what to do is a whole different thing. Businesses can spend a lot of time trying to figure out exactly what to do with this data. Those who nail it, it can be a real competitive advantage that is difficult to supplant because it is not clear how to supplant it. You don’t know what they did by building this proprietary model initially.

Frankel: Yeah, I would be okay with that. As a lender, especially when targeting the subprime mortgage market, these little variables are very important, especially if you’re not trying to give people 20% interest rates on auto loans.

Moser: Yes.

Frankel: It is really important to better assess when people are going to default or not. I remember a statistic from the Upstart presentation that said most personal loan buyers don’t have a credit score that would get the best rates from a lender. But most of them have never defaulted on a loan, or made a late payment, or anything like that, so why shouldn’t they get the best rates? The Upstart formula really tries to lower that and level the playing field, and give people the credit they are owed, I guess you would say, better than the traditional model of just looking at your credit score. .

Jason Moser owns shares of PayPal Holdings. Matthew Frankel, CFP, has no position in any of the stocks mentioned. The Motley Fool owns stock and recommends PayPal Holdings and Upstart Holdings, Inc. The Motley Fool recommends the following options: Long January 2022 $ 75.0 calls on PayPal Holdings. The Motley Fool has a disclosure policy.

The views and opinions expressed herein are the views and opinions of the author and do not necessarily reflect those of Nasdaq, Inc.