The Upstart Macro Index (UMI)

0:02 You're listening to Leaders and Lending from Upstart, a podcast dedicated to helping consumer lenders grow their programs and improve their product offerings. Each week, here decision makers in the finance industry offer insights into the future of the lending industry, best practices around digital transformation, and more. Let's get into the show. Welcome to Leaders in Lending. I'm your host, Jeff Keltner. This week's episode features my conversation with Paul Goo, the co founder and the head of product and data Upstart. Actually this is our second conversation with Paul, and his first episode is actually still our most listened to episode of all time, so we're excited to bring Paul back. It is a really interesting conversation delving into some recent innovations. Upstart is made around measuring the impact of macroeconomic conditions on loan performance and really separating out individual performance of loans from the acro economy's impact on those in a very quantifiable way, which I thought was a fascinating topic. It's a really interesting area of research, so we kind of dive into how it works, why, how that can be utilized in what up Start is working on in the future. Towards us. It's a really interesting topic, one obviously highly relevant in the current environment, and so I appreciated having a chance to dive deep with it with Paul. I will say there's one correction to make upfront, which is that Paul mentions what he called the Upstart Macro Forecast or UMF, and the correct term is Upstart Macro Factor still

1:33 UMF. So just a quick correction and without further ado, please enjoy this conversation with Paul Goo. Oh, welcome back to the podcast. Thanks for joining us again. Oh, I'm happy to be back. It's grown quite a bit since I was last year. It is and yours is one of the most popular episodes the original that we've ever had. So apparently alreadience likes technical discussions. We talked about AI and lending in a more technical way last time, so we're gonna try and give them a little bit more technical stuff. Great, let's do it well. The topic of discussion today that I really wanted to dive into is the topic of what we call the Upstart Macro Index or u am I, because that's been I know, we've talked about it a bunch and earnings we've talked about it publicly. We've talked about it with our partners, but we haven't disclosed a lot about it or gone in depth, and so ill I know some people have gotten one on one, you know, introductions or explanations, but I would to spend the day kind of diving into it. So maybe the best way to just start is like, what is you you am I? Yeah, you AM I stands for Upstart Macro Index. And before I describe what it is, I might take a step back and just describe how we got here and why we started working on this thing that it became known as the u AM I. So if you if you take a step back and look at where we were in call it mid twenty twenty one. At that time, very loosely speaking, almost everybody was doing a good job of repaying their loads. Obviously not everybody.

3:00 There were always defaults, but repayment rates were extremely high compared to historical norms, and it had looked like at the time everybody was a genius in lending. You could have lent to pretty much any type of consumer and probably you're outperforming your expectations in terms of repayment rates and therefore rates of return on debt capital deployed. Then you fast forward another year to mid twenty twenty two, and the story had flipped. Instead of every type of borrower outperforming, now you had almost every type of borrower underperforming. And the change from mid twenty twenty one to mid twenty twenty two was dramatic, and you could see that in a variety of metrics, but it wasn't totally clear how you would precisely tease that out and quantify what had happened in the quote unquote macro environment from mid twenty one to mid twenty two. And we started to have conversations with a lot of our lending partners of the forum, Well, what's going on?

4:02 I you know, I all I see is that delinquency rates have gone through the roof. I don't know if it's because the up Start decided that, you know, has upstarts model has gone bad? Has Upstart just sort of open the floodgates to low quality borrowers? What you know, servicing degraded? What what in the world is going on? And when you see a very dramatic change two x three x, they weren't talking large multiple in a short period of time. People naturally get worried and they want to know, and of course we wanted to know too, and we had a pretty good sense from the indirect metrics that we we had, of course kept our eye on, but it wasn't precise in the way that we would like to have had it, and so we said, well, we really want a precise quantitative way to tease apart what we call the macro and the micro effects of underwriting. And more precisely, what I mean by that is, if you think about what an underwriting model does, the one hand, it has to separate risk, meaning it has to say this particular applicant is more likely to default than this other one, and they're more likely to default by two times.

5:06 But another thing it has to do is it has to figure out the absolute levels of default risk. So that first baseline borrower, what does a nearly risk free borrower look like, what does a super risky borrower look like? And what is the average population and default rate going to look like? And the reason that those are such separate problems is that for that second problem, you really have in some sense very limited amounts of historical data to train on in the way that you would like to train an mL model. Whereas for the first problem, the risk separation problem, you have an enormous amount of data that you could look at. Basically, every single default that's ever happened is mostly a story of relative default. It tells you that, within a given period of time, how likely was a particular borrower characteristic to default compared to some other borrower characteristic. Whereas to look at the average level of default in say a year, Well, you only have so many years on record, and you certainly don't have the thousands or millions of data points that you would like to have. I mean, human history barely goes back that far. And certainly we weren't recording our loan repayments, you know, going back to those days. So that makes it very challenging. And so we sort of have are just like a handful of meaningfully different periods recessions and non recessions. You can think of it as like, but maybe like twenty data points in recorded history, and twenty is just not enough for any kind of serious machine learning training problem. And so we separated this sort of micro question and this macro question, and we said, okay, how can we just

6:36 precisely measure the macro component and know whether a period of time is seeing a increase or decrease and of how much compared to pass periods in its average level of default across the population. So that's that's that's what we wanted to know, and about eighteen months ago we started pouring a lot of our a lot of our research science attention to this problem and the end result is something that today we call the u am I the Upstart Macro Index, Yeah, the Upstart Macro Index. Essentially, it takes a It aims to tell you if you had constant borrowers, if you're just constantly making loans to the exact same group of people across different periods of time, what would the delta in their delinquency rates be in different days, weeks, months, years, whatever time frame you want to compare. And the way it does this is by making use of what we call a reference model, because of course you can't actually find exactly identical borrowers every single year to make loans too, and no matter how you control it with one variable two variable, you might say, well, let's just look at you borrowers who are six eighty to seven twenty on the FICO scale, and that would be a very simplified way to do this, but of course there are a million other things to know about these or is other than their phycho score, And so the way to do that in a more holistic and continuous way is with what we call a reference model.

8:07 So you say, what if we underwrote all of these these loans with exactly the same model, because of course, in reality, every loan you have on your books was underwritten with probably a different model at a different period of time. But if you instead underwrote them with exactly the same model then made predictions for every single month that you've subsequently observed, how do the actual delinquency rates and default rates compared to what a constant reference model would have predicted. And what that tells you the reference models doing the work of controlling for the consumer. And then what you can observe is, of course the actual loss rates in real calendar months compared to what the model would have predicted on this sort of abstracted, hypothetically constant kind of calendar time period. And so the deltas in those observations compared to a sort of now controlled expectation of default or delinquency is going to tell you how much more or less risky twenty twenty two was compared to twenty twenty one, compared to twenty nineteen, compared to twenty seventeen. And so that's that's what we've developed. We call it the Upstart Macro Index, and it does a really good job for us of both explaining how sort of past delinquency patterns have played out and why they've played out that way, and also actually in being able to make forward looking statements of the forum. Well, if the macro environment gets fifty percent worse, then this is what will happen to your loss rates. And being able to make statements

9:41 of that form, of course, then allows us to make useful statements about how we should be building in buffer and conservatism to the underwriting for any given lending partner, you know how aggressive or conservative their parameters are set in how much lending they wanted to. So a really useful both backwards looking and forwards looking. So I got a number of questions to dive off this one of the things you said, But first I kind of want to be really clear when when you produce the index, it's a it's a singular number for any given month, as I understand it, what is how should still want to look at the number and say, what is this? What does this tell me? If it's a one point zero, a two point zero, a zero point file, like, what what's the actual index? And how do I think about reading it? And then I want to dive into a bunch of things that you said about this. Yeah, so the index is is condensed down to a single number, as you just said, and that single number can be can be applied to any any length of time. So usually we talk about it in one month periods because most of our loans have one month repayment period, so it makes a lot of sense to look at it that way. But you could look at them in days, weeks, years, quarters, however you like. But four a period of time, you're going to have a number, and that number is going to range called between zero and three generally, though of course there's no theoretical upper meant to to how high the um I could go. But what we've state, what we've normalized the numbers to mean, is that is a one dotto generally is meant to correspond to a what we think of as a sort of historically normal time

11:13 or at least historically normal time in our recorded history, but you can generally think of as being the sort of five years before covidum, and those those five years there was relatively sort of a stable macro environment. We did not see large changes. You know, again, taking that reference model approach, if you're just underwritten all the loans using the same model, you would basically see the same sort of results across across the different calendar years, whereas u oras after that. Of course, once you get into the COVID world, you see both large positive and negative shocks to that, which is exactly you know, what this methodology is hoping to tell us about. Yeah, I imagine that the COVID period, particularly the very serious economic impact than the rapid an input of stimulus and then the rapid withdrawal of stimulus, was like changing of macro conditions on steroids, or at least at fast forward speed in terms of a normal cycle, which I think is kind of what was some of the impetus for this is that kind of rapidity of change. What we usually think of is maybe not a super slow but but not not as rapid of a of a changing environment as we experience over the last twenty four months.

12:20 Yeah, totally. I mean, it was almost a perfect couple of years to showcase just the difficulty of the macro prediction problem, which you know, we've we've always a felt was not really a good a good prediction problem in the sense that these you have so few of these events, as we talked about, and each shock looks really different, and so trying to predict them based on you know, pass shocks looks kind of silly. And I mean April twenty twenty was probably the most extreme example of this, where April twenty twenty hits And of course we have we have we've built over the years plenty of what you'd call macro prediction models that look at things like unemployment rates and UH and and and UH and various sort of macro indicators that unemployment generally has in past shock's been the single biggest driver. But what happened in April twenty twenty while unemployment rates went through the roof a sort of um never before seeing a rapid rise in unemployment, and yet what happened to loan repayment, Well, it turns out that within a very short time, loan repayment did not only did not get worse. It became the best period of loan repayment probably ever in all of human history. Um and uh. And it was because, of course, the you know, the government responded very forcefully to the increased unemployment the pandemic and um did a lot of stimulus in various ways.

13:41 And and people had a lot of extra cash to make their loan payments and uh and and not as many places to spend it because they were locked up at home um and and so you you've got exactly the opposite effect of what sort of historical precedent would have told you. And then if you look at twenty twenty two, you get almost the mirror image of that, where you have extremely low unemployment, basically pushing records in terms of how low unemployment gets, and yet you have this rapid rise in delinquency rates. And it's for exactly the same reason. The stimulus ends. People still had jobs, But it turned out that printing money and giving it to people had a bigger impact on whether they would repay their loans and seeing if they were working or not.

14:26 So I want to ask about kind of how traditional lender. I mean, this is certainly the topic of how is the macro economy playing into loan performance? Every time I talk to, lenders are looking at inflation rates and interest rates and unemployment rates and trying to understand what that's going to mean or is doing to a given portfolio. So how does how do you think traditional lenders have looked at the kind of problem you're trying to model, or at least the data point of, like what is the macro environment doing to the loss rates in a pool? In? What are the as in the way it's traditionally been done that you were trying to solve for when you thought about building out the U and my methodology. Yeah, so I think there's there's spectrum of approaches, but they share a couple of things in common. The first is that because many traditional lenders don't change their underlying models very much, or they have very simple ones that are have a very limited number of variables, they can kind of make an assumption and it doesn't seem as crazy as it does in our world, though we'll get to why it still suffers from something the same challenges, but it doesn't seem as crazy to make the assumption that, hey, we are underwriting with a constant model and so the barrow wars that we produce across different years should roughly be the same. And if they're roughly the same, then I can understand where the macro is just by looking at the average default rate in my own portfolio. And this is this is sort of okay. It's sort of okay because if you actually don't change your model in any way, then actually you do have a fairly sort of

16:00 constant model. But of course it also assumes that your barrower is your barrower mixes unchanging across time, that your sort of pricing approaches have not changed across time, and of course that your model actually hasn't changed in any way across time. And of course we know that even if you just were using say the Phyco scored down right, of course the Phyco score distribution that are changing across time and inputs to it, you know, are are are getting changed by you know how medical you know, bankruptcies are handled in sort of different things like this. So there're actually a bunch of these changes happening under the hood. And maybe they're not that extreme, but but put together, they're probably each you know, ten twenty percent type effect, and soon you could be in this world where you might be seeing default rates that are fifty percent higher and now you have to you have to ascribe that to macro, when in reality it might just be that your barrower mix change twenty percent and your your underwriting model changed twenty percent, and and there you are with the fifty percent. So that that's that's that's pretty inherently challenging to measure macro in And then I think on the sort of response side to macro, I think it's it's also when you don't have h we don't have sort of a precise factor that's able to separate what your underwriting models is doing and what what is happening in the macro. There's always this temptation to say, well, we can fix the problem just by changing the underwriting model. So if we only focus on higher phycho barrowers or higher income borrowers, then then we don't have to

17:32 worry about the effects of a recession or the effects of a macro shock. And I think that that is an approach that really can get you into trouble where you know, you look at a lot of pass recessions something like two thousand and eight, and you look at what happened to credit card delinquency rates in two thousand and eight or mortgage delinquency rates in two thousand and eight. And what you see is actually that the largest multiple increases to delinquency and default rates were in high phyco buckets. Maybe it's a little counter tuitive, but then if you think about what was happening in two thousand and eight, of course, one thing is that the biggest stress for on people who were buying large homes and had big, big mortgages, and and of course that's going to be a primer consumer um. And another thing is that, of course it matters quite a lot, you know, the kind of shock in the economy and whether that's something that's going to impact more prime people or less prime people. But but some of some of the less prime people actually m in some sense are like always in a recession, they are kind of living paycheck to paycheck in a way that means their lass rates are are normally much higher, but it's also harder for them to get so much higher. Whereas you know, when you have someone who goes from being comfortably sort of like you know, putting money in the bank every month to suddenly loses their job.

18:45 It's it's sort of a fairly tremendous change in their ability to pay things. And of course the dead oppligations are much larger. There's sort of less kind of ability to easily make up for it just by um by you know, uh going to backup sources of cash and so there's these different effects that play out. But but it's it's very hard, I think nearly impossible to solve for macro problems by changing the borrower level characteristics that you want to write too, because there are no set of characteristics that are inherently a recession proof or macro shock proof and um and even if even if there were, frankly, I think we don't realistically have the historical data to identify what those are today.

19:32 The other thing that occurred to me is I was reading through the approach to you, m I is the sense that particularly to see things in real time, you know you not only mean what you've really said is to do this right, I need a way to hold the bar or based constant, some sort of a constant reference model, the credit model constant. But I also need really an individualized risk prediction and ideally a month based risk prediction, because if I want to see how it happened, what happened in this month, I want to see that I expect this some months or every you know, every given month of se reasoning that could be for your loan portfolio exists in the portfolio somewhere, and you want to know is this loan that went delink when a month thirty two? Was that unexpected or expected? And so you need really a pretty precise model of risk to be able to see this in something like real time, I mean not real time, but to see it rapidly and quickly and to be able to adjust. And so it occurred to me that the kind of individual risk prediction and loan level and month level risk predictions in the reference model are really critical to being able to see not just with granularity but with speed what's actually happening in the environment and how it might be changing than the underlying from what the underlying predictions might have expected.

20:37 Yeah, that's that's totally right. If you only have lifetime default probability predictions, or you only have those for certain buckets of borrowers, and you're not going to be able to do this then, and you won't be able to control for the borrower mix at all, well with a reference model that doesn't consider enough individual characteristics. And if you if you only have a lifetime prediction, then of course you can't compare what's going on in different periods of time. So you really need a model where you have a lot of confidence that you know, the month seven prediction for this particular individual really is a good prediction, at least in relative terms relative to your predictions in the other months and relative to your predictions for other borrowers in that month. And if you have confidence in that, if we think of as you know, if there are months on the sort of X axis and borrowers on the Y axis, you need to feel like both your axes are really doing a lot of work for you, that it's sort of an unbiased estimate. And if that's the case, then you can actually take that point on the matrix, if you will, and compare it to other points on the matrix, and it tells you something meaningful. And of course if you don't have that, then you can't do that comparison. Yeah, so I did want to ask you call this the macron actually talked about the macro and micro prediction levels of the model.

21:55 And it's interesting because macro can be a reference to the macro economy, the kind of broader world, but it's also kind of size metric macro and micro, And so I kind of want to just ask the question, like, how do you think about the relative importance in any given moment or overall for the micro portion of what you might call the core risk modeling that up starts being focused on and this kind of macro level that's maybe harder to predict but now somewhat more measurable through you am I how do those kind of stack up in terms of how important they are to a lender into a lender's portfolio performance. Yeah, so there, I might first say they're both really important. They're both important in the context of you know, fixed income of any kind has this property that you can lose a lot more money than you can make. That's that's the nature of fixed income, and that means, you know, generally, anything that can meaningfully increase your default rates is something you're really going to care about. And certainly both the macro and the micro here fall into that bucket. If you get those really wrong, it's going to really affect the return you were expecting. Now, having said that, if you were to just force a competition between the macro and the micro, how much can losses vary based on macro and how much can loss is based on micro? I mean fatly, then it's not even close. Because the macro, you know, you can get you can get a period of time that's three or four maybe in an extreme pace, five times as bad as another period in micro. Of course, you can get borrowers, and not just theoretically, but even identifiably. For example, in our model, you can

23:29 identify borrowers who are like eighty percent likely to default, and you can identify borrowers who are zero point eight percent likely to default. So you know, you're talking about a one hundred x spread between the sort of highest and lowest risk in micro, and you're talking about a five to one spread in the highest and lowest risk in macro. And so, of course it's so much more important to get the micro right than the macro right. There are so many more ways that you know, even in the best of times, you know, if you try to go to market and underwrite with with an extremely poor performing model, just everything will go wrong. And because not only because your model will be wrong. You know, you face adverse selection because other lenders will pick off at lower aprs the better borrowers. I mean, just so many, so many things can can go wrong in micro, whereas in macro things can also go wrong, such as you know, when you go from a really really unreasonably good period like twenty twenty one to really a sort of sharply bad period like twenty twenty two, that's that's going to significantly and negatively impact lender returns. But it's still it's still going to be on you know, you know, if we're talking about annualized return impact, I mean depending on what your risk mixes. I mean you're still talking. You know, you can count it on your two hands, like the number of percentage points of impact that's going to have. WHEREA if you get the micro wrong, I mean, there's there's really no limit to how much money you can lose doing this. And and of course on the flip side, you know, when things are going well, micro is what enables you and has enabled

25:02 the lenders that use our platform over the years to be able to make dramatically more more income running a lending business. Because micros what enables you to confidently expand your approval box while holding your risk levels constant. So if you can improve fifty percent or one hundred percent or two hundred percent as many as many borrowers as you previously could, but you get the same risk levels, then of course you know suddenly now you're able to meaningfully change the amount of lending income being general. Yeah, interesting, Well, I want to dive in a different topic you made this comment about, like if you can model out if the world the macro got fifty percent worse or I'd love to say fifty percent better. Sometimes I worry we talk about the macro, we only talk about bad, talk about macro getting worse and protecting, and not the fact that, particularly from where we sit as we're recording this, there's a lot, probably more upside for the macro getting better than the substantially worse over the next at least twelve or eighteen months. But the interesting thing is you haven't talked really about what I would consider traditional macro variables. Right, Like most people when they talk about how is the macro doing? You know you have a um I you'll talk about where it's at, But most people look at inflation unemployment, interest rates, maybe savings rates, things of this nature that are very clearly tied to what we think of as a macroeconomy GDP or something like that. What is there a relationship or those part of the U and my model. Talk to me a little bit about how like traditional views of what is happening in the macro relate to the Upstart macro index, or how you think about the impact of macro and the lending portfolio. Yeah, yeah,

26:36 they're they're they're super correlated. In short, the upstart measured you and I. We like it because it has the nice property that it's directly applicable to the math you want to do on lending um, and because it's it's really specifically designed to tell you this period is a period in what you can expect twice as many deligencies the same borrower pool as that period. You know that it lets you do math in a very precise and direct way. But of course, UM, it would be really concerning if this index that's meant to measure the macro is totally unrelated to the sort of traditional macroeconomic variables, which, of course you know, though each one maybe only tells part of the story. They are collectively, you know, a pretty good description of the things that we care about in the economy and UM and so we have that that's been an important part of developing the UUMI is actually building a sister model that tells us what we We haven't found a nice, sort of externally marketable name for it yet, but if you think about there's sort of um I as measured in the sort of collective repayment rates of the of all Upstart platform originated loans where we have, you know, access to the data.

27:52 But then there's there's uum I as you would predict based on what you're seeing from the the sort of official macroeconomic data, the unemployment rate, the inflation rate, the personal savings rate, and and what you want is you want to see that these two measures, they sort of internally measured UMI and the externally inferred UMI are largely moving together, highly correlated and kind of moving together, and UM and that's that's exactly what we see. We've been able to see that, and actually you can UM you know. The maybe short and snappy version of this is if you just want what single variable released by the FED can tell you roughly where the UMI is going, and the answer would be the personal savings rate. That of course is a bit cheating because the personal savings rate itself is a bit of an amalgamation of a bunch of variables.

28:45 It's, you know, looking at personal and broadly looking at personal income and personal expenditures. But of course what makes up personal income. You know, people have to work, so there's employment rates baked into that, there's wage wage growth baked into that, and of course on the personal expenditures side, there's sort of your real rate of spending, and then there's there's the inflation rate. And so you've kind of got this one variable that the Fed publishes, you know, the end of every month, and it tells you roughly the things that really matter unemployment, inflation, spending, and wage growth. And the net of that sort of is like how much money people have left over, which is a really good proxy for, you know, how much money people are going to have available to service their their debt. And if you just look at that one variable, that's probably like you know, mostly mostly correlated with how we've measured you and I over the past years.

29:36 Yeah, it does seem like a i won't say a cheating variable, but it is an amalgamation that that takes into account a number of the things that people traditionally think of as pretty impactful to at least particularly unsecured credit, where there's you know, it's kind of the I want to say the riskies, but the bottom of the payments to act in any ways, where the first thing to take take a hit when one times get tough. So one thing we haven't talked about today at all, and I'm sure our lending partnership seems to be very upset with me to be this long to ask this question, But you know, I think there's obviously when you and I goes up, macro gets riskier. There's this question of is that a direct indication of loans under or overperforming? And how does the sense of the macro play into how you actually work with a lending partner to assign a level of risk to a borrower at time of underwriting and understand the returns produced by that portfolio. So I think the thing that I hear a lot is like does a U am I above one? Meaning all my loans are underperforming because the macro is high, and therefore I'm losing money and that's a bad thing and I should stop lending or whatever. So talking about how you leverage this in the context of partnerships with originators to kind of calibrate to what's going on and help them understand the level of risk in the environment that's going into their originations. Yep.

30:49 Yeah. So in short note, it does not there's no direct way to say you am I is a certain number, therefore my loans are either we are underperforming. To know that, you need to know one more thing, which is essentially what you and I were you assuming when you made the loans in question, and that that particular thing we call the um the macro forecast. And if you very roughly speaking, if you just for any batch of loans, if you take their UMF and you then look forward and say, okay, I made this batch of loans in January of twenty twenty two, and at the time we had a UM of one dot O and and now the UUMI is one point five. Then that sort of implies that you're going to have actual losses that are fifty percent higher than forecasting. In that case, sort of the example you gave as valid. Now fast forward to to more recent times, and many of our lenders actually have a much higher UM.

31:55 Imagine your UMF is two doto, but the uum I that's in observe sense is only one point eight. Well, then, actually, even though one point eight is a really high number by historical standards, UM it's actually twenty or it's actually ten percent lower than the UM that you assumed. And and so that means that your loans were priced as if you were operating in a two doto type world. But actually you've been seeing a one dot a type world. And now you're going to see defaults and delinquencies that are running on average ten percent lower than than than you were expecting, which of course means uh, you know, more more sort of net interest, more more excess returns, and so returns will be higher than than expected. And of course you know it, Actually it matters how this plays out over the whole sort of term of the loan. But um but you know, just roughly, as an approximation, if you think about a single point in time, this kind of tells you. This, this ratio between the um I and UM tells you how things are going to be. And so if you underwrite with a fairly high UM, then of course there's more room for um I to positively surprise against that. On the other hand, if you want to write with a high UMF, you're going to be passing up a lot of borrowers and pricing a lot of other ones out of out of out of converting, just because you're assuming that you know, the world is in a really bad place and you want to, uh, you know, lend to people who, uh you know, who are going to be going through a really hard time. And of course if if if they aren't, or if you

33:27 know other lenders are not seeing it that way, then those borrowers are going to go elsewhere. How how can you help a lender think about I mean, what a UUMI or UMF of two or one point eight or one point five, Like, I feel like that's not something that at least as of yet to be great for you. If that became something about which people had an intuition and a made a natural understanding, it was like a number they were used to kind of thinking about where it may trend and where it may fall. But how do you think about, like what causes a um I or UMA to get to a certain level? Can you I mean, I think that scenario plan. You know, if you think about just the Dot Frank stress test kind of thing, if unemployment goes here and somebody goes here, like, how bad does that get? What will have my portfolio?

34:07 How do you think about connecting the dots between those that the concept of you know what might happen and what that'll mean to you know, where these loans could be performing. Yeah, I think they're two good ways to build intuition around at these UUMI index values. The first is to go back to that personal savings rate, which is largely correlated, not perfect but pretty good and again includes the unemployment and inflation, all all the pieces, and and what you can basically see is that you can think of it as a historically average level of the personal savings rate. Let's just be round numbers. Call it on the order of ten percent, roughly corresponds to a sort of normal UUMI condition of around one point zero. And then you know what happens, of course, if the personal savings rate goes up. You know, if the personal savings rate goes up to something like twenty percent, which you know basically never happens except in in twenty one when you know people are given lots of money. Yeah exactly. Um, but you know when you when you get something like that, then you see you and I basically get cut in half down to about zero point five. And again I'm just speaking in round numbers here and then um uh. And then on the on the other hand, UM, you know you can see you and my values go uh, you know, go from one point zero to two point zero. If you basically, you know, roughly speaking, cut your personal savings rate in half, which is, you know, on the order of of what we've seen over over the past eighteen months or so. And then the other sort of way to build intuition is just to look at different periods of time. So again

35:38 you and I one dot O roughly corresponds to the five years before the COVID period. UM in the sort of um, happy days of free flowing stimulus money. Um, you know, you've got you of mys that go down to nearly zero point five and then um and then uh, you know, stimulus running out producing that large shock takes you, you and I over one one one one point five. And then if you were to sort of look at historical values of personal savings and you and I sort of asked the question, well, how bad can it get? At least how bad have we seen it get historically? Probably the answer is something like, you know, in the worst times ever that again in recent recorded history, we have all the relevant economic data, maybe something like the worst month of the Great Procession.

36:20 We think you and I would have been in the high twos. Interesting, So I get two more things I want to hit on, I think, and then I think we've kind of at least gotten a good intro for people into this concept. One is, we didn't really talk about this, but You and I as you've built it today is really based explicitly on unsecured installment loans, particularly the kind that Upstar partners with banks and credit unions to originate. Are there intentions to build something like You and I for other asset classes? Is it applicable to other assets? Like? How do you think about the usefulness of it as a construct or the limitations of it as a construct given that it's really a measurement specifically on a particular category of consumer credit. Yeah, great question. Um so we don't we don't see um I as something that you just develop methodology once and it's done. I mean, nice if it was like that. But really it's a very sort of rich um surface to explore, because there's not only the question you mentioned, which is a question of you and my for different products, but there's actually you a mid for different types of consumers. And while maybe on average they will all move together, they don't, of course exactly all move together. Their slopes are a little bit different, their sensitivities are a little different, and um, and so what we really are. You can think of the progression of you and my methodologies as going from first you sort of assume there is just one UOM quote unquote working off one reference model. Then you have one UUMI that's produced actually by an amalgamation of reference models, and that sort of

37:52 gets, you know, more and more continuous as you go from you know, one to two to end and then and you really get to a methodology that that's sort of much more continuous with the back to your reference model. And then you have a sort of second dimension of you and my methodology improvement, which is really about going from assuming sort of quote unquote the average borrower to really making it something that where the you and I is interacting with the borrower characteristics, not unlike how we see all the sort of the other work we do in in in the sort of prediction realm is there's just interaction effects going on between almost any given characteristics of a borrower, and of course those also interact with macro and so those should those should be considered. And then the last sort of dimension is is the type of loan it that it is, and that's you know, true of it, of its size, of its duration, of its type, and so that could be it being an auto loan, a personal loan, a three year loan, a one year loan, or um or any sort of combination of these. And and so there's there's there's a lot of sort of continuing research into you and I.

38:53 That's that we're doing. And having said all that, the good news is that we think even this first of you and I, as the first approximation if you just want to answer the question of under what conditions will my loans over and underperform and by roughly how much, you're going to get a very good approximation just from you and I V one. That is is true, it's built on unsecured personal loans, but you know, we look at it in the context of our other products like our Autorefi products, and again it's it's not quite as precise, but it does give you a really close first order approximation of your level of over and underperformance, again looking at those uom I and uu F ratios of the changes across time. So it does a good job explaining, and that gives us more confidence in the methodology because it tells us that there's something very general happening in addition to the sort of many smaller but more specific things going on within each product, within each type of borrower, and so on and so forth. Interesting. I guess my last question for you is it sounds like this is early days in the development of you am I like a very solid foundation, but compared to the work you put into understanding micro risk is still a pretty pretty immature in comparison and has a lot of room for improvement. And you also mentioned if people want to get an intuition, they should look at the numbers. So if people are interested in looking at the numbers or following along as the methodology and kind of the insights coming out of the work into macro and the u m I evolve, is there a place they can go to see those or they publish somewhere,

40:25 is there are place they can follow along what's happening, Like where can people go to learn more and keep up to date with you know, what's happening to um I and what's happening to the work into looking into this macro concept. Upstart dot com slash You am I just out and we're really excited about it, and it's going to get better and better. But it's going to have the core data there and there's going to be more ways to engage with and play with it and really understand the numbers. So yeah, go go there, check it out, see how those values have changed across time, what they were in different periods of time, And I think that will really build a good, good level of intuition for this. Certainly, it's our hope that this would become a tool of general interest beyond those who are either making loans through our platform or even making loans in general. But really we think it's a it's a really it's a really good and useful tool to just understand what's going on in the world. Upstart dot com Slash You am I. It's not a very original you are l very straightforward and easy to remember, so I guess that's probably better than original, and I look forward to see that. I'm actually really excited that there's we're going to be publishing the data set and so kind of a historical data set. I think there's a lot of rich surface area for innovation on top of it, so I'll be excited to see. And if any of the listeners have questions or feedback on what's useful or what you'd like to learn more about the concept, please do right to us or right to just me and Jeff at upstart dot com, because I think it's actually a really interesting space and we'd love to have real input from all of you in terms of where where we take the research and what we learn next. All right, Paul, thanks for taking the time to joyces Is. I think a great first dive, and I appreciate

41:59 your back for your second time on the podcast. Awesome, great, thanks for having me. Upstart partners with banks and credit unions to help grow their consumer loan portfolios and deliver a modern, all digital lending experience. As the average consumer becomes more digitally savvy, it only makes sense that their bank does too. Upstarts AI lending platform uses sophisticated machine learning models to more accurately identify risk and approve more applicants than traditional credit models. With fraud rates near zero, upstarts all digital experience reduces manual processing for banks and offers a simple and convenient experience for consumers. Whether you're looking to grow and enhance your existing personal and auto lending programs or you're just getting started, upstart can help. Upstart offers an end to end solution that can help you find more credit worthy borrowers within your risk profile. With all digital underwriting, onboarding, loan closing, and servicing, It's all possible with Upstart in your quarter. Learn more about finding new borrowers, enhancing your credit decisioning process, and growing your business by visiting upstart dot com slash foward dash Banks. That's upstart dot com slash foward dash Banks. You've been listening to Leaders and Lending from Upstart, make sure you never miss an episode. Subscribe to Leaders in Lending in your favorite podcast player using Apple Podcasts. Leave us a quick rating by tapping the number of stars you think the show deserves. Thanks for listening. Until next time,