LC FICO vs Loan Grade

[Fred93]

For awhile now I've noticed how each LC loan grade is spread across a wide range of FICO scores.  Justifiable, I suppose, because Grade is a better indicator of LC loan loss than FICO IMHO.  On the other hand investors seem to go nuts over that FICO up/down indicator on the secondary market, as if it were a very sensitive indicator.  I dunno.  I don't have a conclusion here.  I just present a chart...



Those are mostly 5 point buckets.  The software I used didn't want to play nice, so it made a couple of 10 point buckets over on the right side.  Sorry about that.  Doesn't change the picture much tho.

[rawraw]

I think you are focusing on level. Early on in my financial career I was told to always look at level and trend. So level is the FICO score. It is a measure of risk. So that level is spread across grades. So what about trend?

Other than payment, FICO is the only variable that updates. If the loans were regraded each month, this would likely be more predictive. But given its all that we have, what information does the trend convey? I believe it conveys how risk has changed since the loan was made. Credit scores have a monthly standard deviation of like 20 points IIRC. I only care about trends outside this normal range. And I believe it conveys very meaningful information, especially for debt consolidation loans, both in the first few months (showing evidence funds were used as disclosed) and over the life as the borrower goes delinquent on other debts, takes new debts out, etc. 

I made my initial decision based on a level of risk. If that risk is gotten worse, then there is a chance the yield is no longer good enough. If I was presented with that loan today, would I still make it? If the answer is no, that loan is sold without hesitation.

Sent from my SAMSUNG-SM-G935A using Tapatalk

[Fred93]

Other than payment, FICO is the only variable that updates.

I get that.  However, that doesn't mean that it is useful or that it if it is that it is obvious how to use it.

I'm not trying to press a point or present a conclusion here.  I made that chart as part of developing an understanding of how to use FICO scores. 

what information does the trend convey? I believe it conveys how risk has changed since the loan was made.

Good story.  Sounds like there could be some truth to it, but that doesn't make it so.

I made my initial decision based on a level of risk. If that risk is gotten worse, then there is a chance the yield is no longer good enough.

That statement is correct, obviously.  The question is whether moderate changes in FICO can be used to make an indicator that makes us money.  Giant changes in FICO are surely meaningful, because I see them in so many loans that go bad.  A guy drops by 150 points, that loan is gonna croak.  (except I had one that didn't)   It isn't clear tho whether you can get an indication early enough to do anything useful. 

Is a moderate change in FICO a good indicator that will make us money?  I don't yet know.

It would appear that you and I agree that small changes in FICO are unlikely to be useful indicators.

So as you can see from the chart, a borrower could have had an initial FICO anywhere from 660 to 815, and still could have been graded "A", and gotten the lowest interest rates.   (A range of 155 points - or maybe more!)  Astonishing but true.

Suppose Joe's score was 750 when he took out the loan.  Now, a year or two later, his FICO score drops by say 50 points, and suddenly you think you need more interest?  Maybe you do.  Maybe it dropped because something bad happened.  However, on the day the loan issued, he could have had a FICO of 700 and still got the same exact interest rate. How come that interest rate was good enough then for a guy with a 700 FICO then, and suddenly its not good enough for a guy with 700 FICO now?

This inconsistency makes me unhappy.

I'm glad you mention the noise level (standard deviation) in FICO scores.  That's an important piece of understanding how to use them.  I don't claim to have the rest of the pieces yet.

I know many people talk about "FICO trend", as if they can look at those curves of FICO vs time and learn something.   I have a conceptual problem with that.  I see patterns too, just like everybody else, but I don't know that they are meaningful.  Here's the thought experiment that makes me a skeptic:  The history of FICO vs time is known to the credit reporting agency that computes the current FICO score.  They're pretty smart, and would use every piece of information they have to compute the current FICO score, and make it as good a predictor of future default as possible.  This means that if there is useful information in the shape of the curve, they have already used that information to come up with the latest FICO score.  If that's right, you can look at the shapes and "see things", but they will provide you no useful information.

[lascott]

LendingRobot presented criteria across grades in another way that I liked some time ago.
FICO is one of my note purchasing criteria.  I have a floor for each grade I invest in. To me it shows insight into a historical behavioral pattern. Yes, I realize it can be manipulated but I go with the bell curve.

Image: http://i.imgur.com/K0PIELI.png

[Rob L]

Funny, but I just happened to run an interesting test yesterday that seems to be relevant here. It was a quick and dirty test and may have been flawed so take the result with that in mind! Caveat Emptor. Still ...

The hypothesis tested was that a drop of N FICO points below FICO edit of previous month for a Never Late loan could serve as a leading indicator to sell that loan. Since the loan is Never Late it should be possible to sell it on Folio at a discount no worse than -9% and avoid a potentially much larger loss if/when the loan charged off. From the pmthistall.csv file I extracted all vintage 2013 Q1, grade D term 36 month loans. All are fully matured now (either Fully paid or Charged off). Bottom line was that I could find no value for N that resulted in improved profitability. I did not search for a sales discount less than -9% that would make this a profitable strategy and think it unlikely one exists. It wasn't even close.

[rawraw]

Have you read this yet?

https://www.peercube.com/blog/post/fico-score-trends-and-defaults-for-lending-club-loans

And I wish there was a way to automate the FICO spike detection. When my account was only a few hundred notes, I monitored it and sold those that didn't spike or started to lose the spike. But it's impossible with thousands of notes.

Sent from my SAMSUNG-SM-G935A using Tapatalk

[Rob L]

Have you read this yet?
https://www.peercube.com/blog/post/fico-score-trends-and-defaults-for-lending-club-loans

Yeah, quite a while ago. The take away points must have still been in my head; thus the Caveat Emptor.
There is still more work that can be done here.

PS: I took a look at my spreadsheet and noticed that I was measuring month to month spikes, not from origination.
Not necessarily an invalid criteria, but certainly a different one.

[jz451]

I wonder if trying to determine an n level of FICO drop of each month for each grade would be a better determining factor, so say a loan is 6 months old w/ an a score at origination of 670, at month 7-n what would the score have be to indicate a possible default?

Funny, but I just happened to run an interesting test yesterday that seems to be relevant here. It was a quick and dirty test and may have been flawed so take the result with that in mind! Caveat Emptor. Still ...

The hypothesis tested was that a drop of N FICO points below FICO edit of previous month for a Never Late loan could serve as a leading indicator to sell that loan. Since the loan is Never Late it should be possible to sell it on Folio at a discount no worse than -9% and avoid a potentially much larger loss if/when the loan charged off. From the pmthistall.csv file I extracted all vintage 2013 Q1, grade D term 36 month loans. All are fully matured now (either Fully paid or Charged off). Bottom line was that I could find no value for N that resulted in improved profitability. I did not search for a sales discount less than -9% that would make this a profitable strategy and think it unlikely one exists. It wasn't even close.

[fliphusker]

Bigger FICO drops can happen for a reason and not necessarily because of missing payments.  FICO is very sensitive to running a high balance on a CC.  I did this earlier in the year with a balance transfer card.  (Was probably really dumb to do as I do not run balances monthly.)  But I got a limit of 1k on a 0% balance transfer CC and topped it off.  My FICO dropped 47 points.  My overall utilization did not change but because I had such a high utilization on just one card it made my FICO go nuts.  The crazy thing here though that when I made a $25 payment to take the utilization under 80% my FICO jumped over 20 points.  How silly is that?  That is the problem with FICO scores is it does not tell you exactly what is going on with them. 
I do not sell my notes just because of a FICO drop, not sure where I would start selling them due to a drop.  When I buy notes on FOLIO I would not touch a down FICO of let's say 50 points in the past couple of months even with a 20% discount.  Now toss in the fact that the notes might have an IGP recently on it and that note becomes toxic for me.  I do not buy many notes on FOLIO so I can be very picky, but even with being picky I have had FOLIO notes with up FICO and perfect 15-month payment history go bankrupt out of the blue.  (Seeing more go IGP recently which has me more than a bit concerned.)
Rob makes a point where he looks at the FICO not from origination.  If I am looking at a 60 month note that the FICO score was destroyed in the first year, do I care what the original FICO score is?  Or do I only care about how the FICO has rebounded after whatever devastated the score?  I wish I knew what killed the score at the time.  CC utilization is way more favorable than missing or defaulting on payments. 
These are things that make FOLIO notes tough to buy and where the poor pricing makes it even tougher to deal with. 

[Fred93]

Funny, but I just happened to run an interesting test yesterday...

The hypothesis tested was that a drop of N FICO points below FICO edit of previous month for a Never Late loan could serve as a leading indicator to sell that loan. ... From the pmthistall.csv file I extracted all vintage 2013 Q1, grade D term 36 month loans. All are fully matured now (either Fully paid or Charged off). Bottom line was that I could find no value for N that resulted in improved profitability.

Wow.  I've been thinking what to do and I was forming a plan to do something very much like this.  Formulate an algorithm, and then apply it to the payment history file and see if it was possible to set parameters (such as an amount of FICO drop) which allowed one to decide when to sell and improve returns.  You beat me to it!

[Fred93]

https://www.peercube.com/blog/post/fico-score-trends-and-defaults-for-lending-club-loans

Yes.  Unfortunately, there's no "time" information in that analysis.  For all we know, the LC loan nonpayment event may be causing the FICO drop!  I need data that shows me that FICO drops BEFORE the LC loan nonpayment event, so that I could sell early and get out, or be warned before buying in.

He makes an argument that his data shows the FICO drops before default, but that's 4 months too late.  We need to know before the 1st nonpayment event.  There's no evidence in that article to help with this question.

[rawraw]

https://www.peercube.com/blog/post/fico-score-trends-and-defaults-for-lending-club-loans

Yes.  Unfortunately, there's no "time" information in that analysis.  For all we know, the LC loan nonpayment event may be causing the FICO drop!  I need data that shows me that FICO drops BEFORE the LC loan nonpayment event, so that I could sell early and get out, or be warned before buying in.

He makes an argument that his data shows the FICO drops before default, but that's 4 months too late.  We need to know before the 1st nonpayment event.  There's no evidence in that article to help with this question.

When I used to track my performance via interest radar, a significant amount of the loans I sold later defaulted

Sent from my SAMSUNG-SM-G935A using Tapatalk

[Rob L]

My overall utilization did not change but because I had such a high utilization on just one card it made my FICO go nuts.  The crazy thing here though that when I made a $25 payment to take the utilization under 80% my FICO jumped over 20 points.  How silly is that?

FWIW - similar story; about a year ago we got a Citibank MasterCard that pays 2% cash back on everything. The down side is that the credit limit on the Citibank card is maybe 1/3 that of several other high limit cards we have. So, we use the Citibank card for every purchase possible (we don't carry a month to month balance). In a typical month our charges are 50% of the card limit (minimum) and often 80%+. Depending on the time of the month and balance on that one card our FICO (per Credit Karma) swings up or down 30 points or more. As a percent of our total card limits the amount charged each month is gotta be 5%-10% max, but because it's all on a single card FICO goes bananas. (I know; we should get the limit upped on the Citibank card but haven't gotten around to it.)

[Fred]

Suppose Joe's score was 750 when he took out the loan.  Now, a year or two later, his FICO score drops by say 50 points, and suddenly you think you need more interest?  Maybe you do.

Yes, I do.

I compare FICO score of a borrower to credit agency's (S&P, Moody's, Fitch) rating of a company.   When, say, Moody's downgrades the rating of a company, the company's existing bond price decreases, causing the yield to go up, thus "more interest."

[Fred]

From the pmthistall.csv file I extracted all vintage 2013 Q1, grade D term 36 month loans. All are fully matured now (either Fully paid or Charged off). Bottom line was that I could find no value for N that resulted in improved profitability.

How did you measure "profitability" from pmthistall.csv file?