[dompazz]

I've just started digging into the historic data provided by Lending Club.  I'm currently looking at 36 month notes and only on the data prior to 2015.

I had assumed the the variable delinq_2yrs would be positively correlated with defaults.  I'm finding exactly the opposite.

Default

nLoans

0 IP logged F Fred Posts: 282 Effect of Previous Delinquencies on Probability of Default I think a few people in this forum has done extensive "factor analysis"-- https://en.wikipedia.org/wiki/Factor_analysis -- on all the attributes in LC historical data.  Not sure if delinq_2yrs really has a negative coefficient, and if it is statistically significant. However, if you really think your analysis is correct, you should follow your numbers instead of your assumptions -- i.e., buy LC loans with delinq_2yrs > 0. Good luck. IP logged T TravelingPennies Hero Member Posts: 6586 Effect of Previous Delinquencies on Probability of Default I've run some basic logistic regressions, sampled and not, and with other factors included, the coeficient is significantly negative.  As a modeler, anything that doesn't make economic sense, I would generally toss out.  Trying to understand if there is a world where this makes sense. One thing I have come up with is LC's underwriting possibly rejects borrowers with higher delinquencies with a higher probability to default.  Those that make it through are better credit risks and have a lower probability to default. IP logged j jennrod12 Posts: 50 Effect of Previous Delinquencies on Probability of Default If I read that right, you are looking at loans that defaulted and what % of them were from borrowers with delinquincies? Did you look at all loans from borrowers with delinquincies and what % of them defaulted? Jenn IP logged T TravelingPennies Hero Member Posts: 6586 Effect of Previous Delinquencies on Probability of Default from: jennrod12 on December 17, 2015, 09:26:15 AM IP logged T TravelingPennies Hero Member Posts: 6586 Effect of Previous Delinquencies on Probability of Default Interesting info, Is there a difference when looked at by the borrower's number of delinquencies or how many months since the last delinquency? Jenn IP logged AnilG Posts: 300 Effect of Previous Delinquencies on Probability of Default from: dompazz on December 17, 2015, 11:00:46 AM IP logged T TravelingPennies Hero Member Posts: 6586 Effect of Previous Delinquencies on Probability of Default from: AnilG on December 17, 2015, 11:41:25 PM IP logged l lascott Sr. Member Posts: 325 Effect of Previous Delinquencies on Probability of Default from: dompazz on December 21, 2015, 09:19:37 AM IP logged h hoggy1 Posts: 54 Effect of Previous Delinquencies on Probability of Default As I understand it, a Delinquency is 30 or more days late and I don't count one in the last two years against the borrower. By contrast a major derogatory is more than 120 days late and I don't buy notes with any. IP logged Fred93 Hero Member Posts: 612 Effect of Previous Delinquencies on Probability of Default from: dompazz on December 21, 2015, 09:19:37 AM IP logged b brycemason Posts: 152 Effect of Previous Delinquencies on Probability of Default Being stumped by covariance is so 2011 on this forum, but you caught me in a good mood after a pleasant 16-hour day of building loan servicing logic. Data: LC 9/30/2015 extract, matured policy code 1 36-month loans between 3 and 5 years old (out of convenience); various other exclusions I'll cite later. Define prior_delinq to be 1 just in case delinq_2yrs is greater than 0. Useful practice because of the few data points past 1 anyway. Avoids estimation issues. . tab delinq_2yrs delinq_2yrs |      Freq.     Percent        Cum. ------------+-----------------------------------           0 |     39,617       89.42       89.42           1 |      3,493        7.88       97.31           2 |        779        1.76       99.07           3 |        243        0.55       99.62           4 |         73        0.16       99.78           5 |         47        0.11       99.89           6 |         23        0.05       99.94           7 |         12        0.03       99.97           8 |          3        0.01       99.97           9 |          4        0.01       99.98          10 |          3        0.01       99.99          11 |          4        0.01      100.00          18 |          1        0.00      100.00 ------------+-----------------------------------       Total |     44,302      100.00 Observation (single-variable analysis): Having a prior delinquency increases the chance of a charge off event. Logistic regression                               Number of obs   =      44302                                                   LR chi2(1)      =      27.03                                                   Prob > chi2     =     0.0000 Log likelihood = -16924.115                       Pseudo R2       =     0.0008 ------------------------------------------------------------------------------    chargeoff |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval] -------------+---------------------------------------------------------------- prior_delinq |   .2302795    .043396     5.31   0.000      .145225    .3153341        _cons |   -1.94617    .015193  -128.10   0.000    -1.975947   -1.916392 ------------------------------------------------------------------------------ Observation (Multi-variate analysis): This relationship vanishes when controlling for the four horsemen of the consumer credit scoring apocalypse. Logistic regression                               Number of obs   =      44302                                                   LR chi2(5)      =    1575.80                                                   Prob > chi2     =     0.0000 Log likelihood = -16149.729                       Pseudo R2       =     0.0465 --------------------------------------------------------------------------------      chargeoff |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval] ---------------+----------------------------------------------------------------   prior_delinq |  -.0021604    .044922    -0.05   0.962    -.0902059    .0858851 fico_range_low |  -.0153585   .0005158   -29.78   0.000    -.0163695   -.0143476 inq_last_6mths |   .1900362    .013459    14.12   0.000      .163657    .2164155 emp_na_slf_ret |   .4404685   .0522608     8.43   0.000     .3380393    .5428978       loan2inc |   2.286919   .1299917    17.59   0.000      2.03214    2.541698          _cons |   8.213554   .3604598    22.79   0.000     7.507065    8.920042 -------------------------------------------------------------------------------- IP logged T TravelingPennies Hero Member Posts: 6586 Effect of Previous Delinquencies on Probability of Default from: brycemason on December 23, 2015, 04:32:15 AM IP logged T TravelingPennies Hero Member Posts: 6586 Effect of Previous Delinquencies on Probability of Default You are super welcome! Don't take my snark personally . IP logged Peter Sr. Member Posts: 362 Effect of Previous Delinquencies on Probability of Default *giggle*  Welcome, Dompazz.  Stick around, I think you're gonna fit in just fine! IP logged Publisher of the Lend Academy blog See my returns here: http://www.lendacademy.com/returns Print [1] previous topic next topic   P2P Forum Lending Club Discussion Investors - LC Effect of Previous Delinquencies on Probability of Default SMF 2.0.18 | SMF © 2021, Simple Machines RSS XHTML

[Fred]

I think a few people in this forum has done extensive "factor analysis"-- https://en.wikipedia.org/wiki/Factor_analysis -- on all the attributes in LC historical data.  Not sure if delinq_2yrs really has a negative coefficient, and if it is statistically significant.

However, if you really think your analysis is correct, you should follow your numbers instead of your assumptions -- i.e., buy LC loans with delinq_2yrs > 0.

Good luck.

[TravelingPennies]

I've run some basic logistic regressions, sampled and not, and with other factors included, the coeficient is significantly negative.  As a modeler, anything that doesn't make economic sense, I would generally toss out.  Trying to understand if there is a world where this makes sense.

One thing I have come up with is LC's underwriting possibly rejects borrowers with higher delinquencies with a higher probability to default.  Those that make it through are better credit risks and have a lower probability to default.

[jennrod12]

If I read that right, you are looking at loans that defaulted and what % of them were from borrowers with delinquincies?

Did you look at all loans from borrowers with delinquincies and what % of them defaulted?

Jenn

[TravelingPennies]

from: jennrod12 on December 17, 2015, 09:26:15 AM

[TravelingPennies]

Interesting info,

Is there a difference when looked at by the borrower's number of delinquencies or how many months since the last delinquency?

Jenn

[AnilG]

from: dompazz on December 17, 2015, 11:00:46 AM

[TravelingPennies]

from: AnilG on December 17, 2015, 11:41:25 PM

[lascott]

from: dompazz on December 21, 2015, 09:19:37 AM

[hoggy1]

As I understand it, a Delinquency is 30 or more days late and I don't count one in the last two years against the borrower. By contrast a major derogatory is more than 120 days late and I don't buy notes with any.

[Fred93]

from: dompazz on December 21, 2015, 09:19:37 AM

[brycemason]

Being stumped by covariance is so 2011 on this forum, but you caught me in a good mood after a pleasant 16-hour day of building loan servicing logic. Data: LC 9/30/2015 extract, matured policy code 1 36-month loans between 3 and 5 years old (out of convenience); various other exclusions I'll cite later.

Define prior_delinq to be 1 just in case delinq_2yrs is greater than 0. Useful practice because of the few data points past 1 anyway. Avoids estimation issues.

. tab delinq_2yrs

delinq_2yrs |      Freq.     Percent        Cum.
------------+-----------------------------------
          0 |     39,617       89.42       89.42
          1 |      3,493        7.88       97.31
          2 |        779        1.76       99.07
          3 |        243        0.55       99.62
          4 |         73        0.16       99.78
          5 |         47        0.11       99.89
          6 |         23        0.05       99.94
          7 |         12        0.03       99.97
          8 |          3        0.01       99.97
          9 |          4        0.01       99.98
         10 |          3        0.01       99.99
         11 |          4        0.01      100.00
         18 |          1        0.00      100.00
------------+-----------------------------------
      Total |     44,302      100.00


Observation (single-variable analysis): Having a prior delinquency increases the chance of a charge off event.


Logistic regression                               Number of obs   =      44302
                                                  LR chi2(1)      =      27.03
                                                  Prob > chi2     =     0.0000
Log likelihood = -16924.115                       Pseudo R2       =     0.0008

------------------------------------------------------------------------------
   chargeoff |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
prior_delinq |   .2302795    .043396     5.31   0.000      .145225    .3153341
       _cons |   -1.94617    .015193  -128.10   0.000    -1.975947   -1.916392
------------------------------------------------------------------------------


Observation (Multi-variate analysis): This relationship vanishes when controlling for the four horsemen of the consumer credit scoring apocalypse.

Logistic regression                               Number of obs   =      44302
                                                  LR chi2(5)      =    1575.80
                                                  Prob > chi2     =     0.0000
Log likelihood = -16149.729                       Pseudo R2       =     0.0465

--------------------------------------------------------------------------------
     chargeoff |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
---------------+----------------------------------------------------------------
  prior_delinq |  -.0021604    .044922    -0.05   0.962    -.0902059    .0858851
fico_range_low |  -.0153585   .0005158   -29.78   0.000    -.0163695   -.0143476
inq_last_6mths |   .1900362    .013459    14.12   0.000      .163657    .2164155
emp_na_slf_ret |   .4404685   .0522608     8.43   0.000     .3380393    .5428978
      loan2inc |   2.286919   .1299917    17.59   0.000      2.03214    2.541698
         _cons |   8.213554   .3604598    22.79   0.000     7.507065    8.920042
--------------------------------------------------------------------------------

[TravelingPennies]

from: brycemason on December 23, 2015, 04:32:15 AM

[TravelingPennies]

You are super welcome! Don't take my snark personally .

[Peter]

*giggle*  Welcome, Dompazz.  Stick around, I think you're gonna fit in just fine!