FICO Scores and Mortgage Payment Performance
I had an informal discussion with a manager in an MBS IT area last month. Just a general conversation about the field and the data people check. He mentioned FICO scores and I noted that I’m not fond of using them to evaluate a mortgage, especially for first-time homebuyers.
Part of this is simple: it’s relatively easier—even in the densely-populated metropolitan areas (e.g., NYC, SF), and certainly in sub- and exurban areas—to maintain a good credit rating if you don’t own a residence. No property taxes, no major repairs, no appliance replacement, no general maintenance, no landscaping, no snow shoveling. And it’s very easy, especially the first time, to underestimate just how much those expenses will be. Looking at just the cost of commuting, renting, storage, parking, etc. makes homeownership appear to be a better economic decision than it is.*
Well, the Federal Reserve Bank of New York recently released some data on mortgage payments by type. It’s not directly comparable—the subprime and Alt-A loans have a more granular level of data, most especially with respect to late and current payments—but there are some interesting relationships.
I looked at the data for States where the subprime loans are current for either (1) more than 55% of the borrowers or (2) less than 45% of the borrowers, which includes 24 states and the District of Columbia. The overall breakdown was 16 states in the first group and eight states and the District of Columbia in the second.
Of the six states that have more than 100,000 subprime loans outstanding, three—Illinois, Florida, and California—are in the More Delinquent category, while only one (Texas) is in the “so far, so good” realm.**
So I ran a regression on those states and the District, using as factors the percent of the subprime loans that were not Owner-Occupied, the Average FICO score for the state, the percent of subprime loans issued to borrowers with a FICO below 600, and the percent of subprime loans issued to borrowers with a FICO score above 660. The result was
PctwithCurrPymt = –1.18*(FICO>660) + .292*(FICO<600) + .266*(Average FICO Score) –0.9*(Pct Not Owner-Occupied) –93.66
R-squared = 0.4213 (Adjusted R-squared= .3056) F = 3.64 (Prob > F = 0.0220)
However, none of the coefficients passes the t-test.
If we assume that there is a solid distinction between a FICO score below 600 and one above 660, then we must note that the signs of this regression are precisely the opposite of what we should expect. The more loans with an initial FICO score above 660, the fewer the number of households that are expected to be current in their payment. Conversely, the more households with a FICO score below 600, the better the Current Payment Performance should be expected to be.
This would seem to be a Very Bad Regression—both methodologically, since it takes two separate sets of data and treats them as if they are part of the same set and intuitively, since it produces results that are not compatible with rational assumptions—but that may not be so.
California, for instance, has the third-highest percentage of Owner-Occupied Properties, the highest Average FICO Score, the lowest percentage of subprime loans to borrowers with FICO scores below 600 and the highest percentage of subprime loans to borrowers with a FICO score above 660. But it falls into the group where fewer than 45.0% of the borrowers are current.***
Which means that, were you to use FICO scores as an input to your model for buying Whole Loans to securitize, you would likely have bought more currently-dicey CA paper than not.
But, as noted, we may believe this to be a Very Bad Regression. The greatest likelihood is that there is/are (an) excluded variable(s) in the equation. If we consider the entire set of data, this becomes clearer. The regression equation for all of the states and the District of Columbia is:
PctwithCurrPymt = –1.019*(FICO>660) + .6118*(FICO<600) + .7685*(Average FICO Score) –0.38*(Pct Not Owner-Occupied) –422.80
R-squared = 0.1471 (Adjusted R-squared= .0730) F = 1.98 (Prob > F = 0.1128)
The signs remain consistent—and counterintuitive—but there is a much lower explanatory power and it is much more likely that the regression fails the F-test. And again, none of the coefficients passes a t-test.
Adding variables whose signs are more likely to produce indeterminate results—the Average Age and the Average Interest Rate of the Loans—corrects the two original signage issues, but produced a third (and possibly a fourth):
PctwithCurrPymt = 1.375546*(FICO>660) –1.639*(FICO<600) – 1.3423*(Average FICO Score) –0.223*(Pct Not Owner-Occupied) + 16.5340 AvgInterestRate + 0.2632 AvgLoanAge + 775.9700
R-squared = 0.4661 (Adjusted R-squared= .3991) F = 6.40 (Prob > F = 0.0001)
The additional variables have significantly raised the explanatory power of the model, and we now see that the FICO scores point in the intuitive directions. But the Average FICO score has ceased to be a positive contributor to the model, and the Average Interest Rate—the only variable that passes a t-test for significance—indicates that the higher the rate, the higher the likelihood of payment.
So we are left suspecting that the initial FICO score does not significantly affect the ability of the borrower to keep their loan payment(s) current. This also seems intuitive, since a FICO score is a stock variable, while mortgage payments are flow variables.
But, as with credit ratings, good FICO scores can only go downward. And it is very rare—especially in an environment in which there is downward pressure on wages—for a good FICO score to go upward. Indeed, dropping the positive FICO score and the Average FICO score as a variables makes for a better regression:
PctwithCurrPymt = –0.663*(FICO<600) –0.238*(Pct Not Owner-Occupied) + 15.4976 AvgInterestRate + 0.1469 AvgLoanAge – 47.325
R-squared = 0.4466 (Adjusted R-squared= .3985) F = 9.28 (Prob > F = 0.0000)
While the Average Interest Rate still has a counterintuitive sign, we should note that the Averages range from 6.69 to 8.66%—even the high end is neither an overwhelming burden for subprime borrowers nor a level from which it is likely to have been worth refinancing. Additionally, while AvgInterestRate remains the only coefficient that completely passes a t-test, both FICO<600 (-3.17) and the constant (-2.54) are negative for all values within a 95% confidence interval. Dropping Non-Owner-Occupied from the equation sharpens matters even more:
PctwithCurrPymt = –0.6747*(FICO<600) + 15.7738 AvgInterestRate + 0.1400 AvgLoanAge – 50.7117R-squared = 0.4407 (Adjusted R-squared= .4050) F = 12.34 (Prob > F = 0.0000)
With the t-values for both FICO<600 (-3.25) and the constant (-2.83) now both more than 99% probable and, again, the values being negative for the entirety of a 95% confidence interval. In summary, the use of FICO scores as a predictor of mortgage repayments appears to be questionable at best, for the same reason that “junk” bonds tended to outperform high-grade securities on a risk-adjusted basis: it is much easier for a rating to decline than it is for it to improve. The value of a FICO score as a predictor of loan performance appears to be much more for lower scores than it is for higher ones. Whether there is greater value on a risk-adjusted basis, as there legendarily has been for corporate bonds, is left for further, more detailed research. *None of which is to suggest that the non-economic reasons aren’t valid. But credit scores deal with how you manage credit, and how you manage credit has to do with the options you have as much as the choices you make. Homeowners have fewer options on the allocation of funds to lodging than renters do. **New York State and Ohio are in the middle range.with 46.8% and 52.0% current, respectively. ***Only Hawaii had tighter FICO standards than California—and they have the second-highest (worst) level of non Owner-Occupied Subprime loans (and the worst of any area with more than 10,000 subprime loans outstanding), while California is fifth-best (lowest) in that metric.
So you run a highly aggregated regression, with only 51 data points, and the single most important variable, negative equity, omitted (hint, California delinquency is probably high because prices are falling, not because FICOs are high), and use those results to ignore the hundreds of studies done with a full set of covarites and loan level data?
Be my guest, but don’t be surprised if hordres of ivestors don’t fall in line behind you.
Mort: You beat me too it. But the Angry Bears have persistently proven that they are unaware that adding one variable to a regression can flip coefficients upside down and right side up. They prefer the single variable regressions of GDP growth versus stated religion of the POTUS.
It looks like a lot of the regression predictors are highly correlated, making interpretation difficult. For instance, higher FICO borowwers tyoically get better rates. Also, since you are looking at subprime loans, a person with high FICO scores that is taking out a subprime loan has to have Something Else Wrong with their finances. I think there is a good chance that the negative sign on the FICO scores is indicating otehr financial factors that aren’t in the data set.
Ed: Ease off. You can’t expect the Angry Bears to understand multicollinearity.
http://en.wikipedia.org/wiki/Multicollinearity
We’re still trying to get throught the unit root lesson.
There is an explanation for the counterintuitive coefficient on FICO scores. Traditional subprime lending was done at high rates to low-income individuals with low FICO scores. This type of lending had higher (teens) delinquency rates traditionally, but it was consistent and the increased yield on the loan made up for losses.
The higher FICO score lending you are seeing was different: done at lower yields to higher-income individuals who were essentially speculating on homes. These were done with no documentation and high CLTV’s. They are defaulting in droves, and the intitial yield on the loans never envisioned such high loan losses. The people that modelled losses on these loans were fooled by a limited data set rife with auto-correlation (House price appreciation leads to low defaults leads to more lo-doc lending leads to more demand leads to more HPA).
In short, I believe the lower the FICO score, the better underwriten the loan was, the higher the intial expected losses, the higher the yield and profitability, and the more consistent the loss experience.
There was nothing wrong with traditional subprime lending. It made higher-risk loans and was well compensated for it despite high losses. Then came the housing bubble…
I wonder if this was not also a factor: FICO scores were among the desiderata for granting the loans in the first place, and so wouldn’t you expect someone with a low score to be more highly rated on other criteria? Given that, wouldn’t we expect to see no correlation at all? (Assuming that the lenders are making accurate assessments.) Couldn’t the counterintuitive results just mean that the lenders were overcompensating wrt FICO scores?
BTW, I also have doubts about the predictability of FICO scores. 🙂
This post seems to reveal a glut of smug regarding the level of thinking in Texas. Or, perhaps Texans are as limited in their thinking skills as so many seem to believe, but some other US citizens are even more limited. With so many so certain that more education is what this country needs in the 21st century bla, bla, bla, this glut of smug seems to suggest that an oversupply of ‘educated’ citizens may lead to unintended consequences. But without knowing if Texans are as backward as some suggest, or if other US citizens are maybe even more challenged, it is difficult to make any sense of any of this?
Sorry — I seem to have somehow posted a comment in the wrong thread. I’ll try to move it. If you come across a comment here that seems even more out of context than usual, I failed.
***In summary, the use of FICO scores as a predictor of mortgage repayments appears to be questionable at best***
Sure, I would make that … In summary, the use of FICO scores as a predictor of mortgage repayments during a housing price boom appears to be questionable at best
When purchasing a necessity (housing) turns into gambling, FICO becomes a limit on the size and nature of one’s bet. It would not be surprising at all that constraining the bet might have the affect of reducing the future problems of those with low FICO scores and increasing the problems of those with high scores.
http://en.wikipedia.org/wiki/Ecological_fallacy
http://en.wikipedia.org/wiki/Multicollinearity
are you counting properties already foreclosed? it could be that the first wave of problems disproportionately hit low FICO borrowers and so the dataset is already “cleaned” of low-FICO borrowers in areas with serious problems.
I think no matter what we want the best credit score at all times. Writing dispute letters and sending them to the creditors can be frustrating. My FICO never changed until I finally found a non profit that had lawyer style credit dispute letters. They ahve inquiry removal letters which always boost even the best credit scores. BestCreditRepairLetters.com is a site ran by volunteer credit repair experts that offers credit dispute letters for credit inquires, late comments, collections, charge-offs, etc. They have examples on the website that show their letters work. Also inquiry removal helps and there is a non-profit group that does credit inquiry removal.
FICO discriminates between borrowers within a market. The distinction between borrowers in different state is being driven mostly by housing price inflation and subsequent housing price collapse (or the lack thereof). The single biggest factor in default rates is loan to value. Rational distressed homeowners with equity in their homes sell without showing up as defaults on the bank’s books.
Simply put, you don’t have the right kind of data to determine if FICO scores are useful. Other factors swamp this one.
Also, your assumption that FICO scores don’t take into account lack of credit experience as a factor probably overstates the situation. FICO scorces don’t simply start at perfect and work their way down as you make mistakes. One of the classic ways to boost a score is to get lots of credit, to regularly use a small portion of it it when you don’t have to, and to promptly pay that small portion that is used. Absent intentional manipulation, which most first time home buyers aren’t sophisticated enough to engage in, these sorts of FICO score elements moderate the first time home buyer effects you describe.
How do they exactly compute for FICO? I just got my FICO from equifax and was surprised to have only 660. I had always been a good payer with Capital One, but there was only this one time when I had a late payment. But that’s just for a few days, how come it affected a lot. I’m thinking that maybe because I cancelled my card with them, and they reported it. I had missed payments with other cards before but they don’t seem affect my FICO at all. How could a missing payment cause too much impact when it comes to cap1. and to think Capital One doesn’t even offer cheap loans at all.