Lend Academy Network Forum

Lending Club Discussion => Investors - LC => Topic started by: Rob L on January 12, 2014, 12:57:45 PM

Title: What's This "Best Note" Selection Business Anyway?
Post by: Rob L on January 12, 2014, 12:57:45 PM
Been thinking of writing this a while and have an hour or so before football. Folio users may ignore this thread. That's an entirely different animal.

Before we see any loan LC has reviewed it in sufficient depth to its own satisfaction to assign an interest rate sub-grade. Not only do they have all data that is eventually available to us in the browsenotes but, given direct access to the borrower, they clearly have much more. They have a team of seasoned professionals that lead the underwriting process and they have been doing this a long time. They have developed a proprietary loan scoring model and every bit of historic loan data available to us is also available to them. They have access to expensive historic data from the credit bureaus likely not economic for the rest of us to obtain. Finally, history has shown LC has done a pretty good job of achieving its goal to "... provide higher risk-adjusted returns for each loan grade increment from A1 to G5." (actually not so well with D, F and G).

LC policy makers select an interest rate structure that they feel will maximize their fees at any point in time, and loans are uniformly underwritten to conform to that structure. All loans graded XX on any day are to the very best of LC's ability the same and no loans are improperly graded XX when they should be YY.

So why is it that we believe we can use a subset of the data available to LC, filter for zero inquiries, no business loans, income >$3k/mo., etc. and get the "best" notes? Typically when we filter we filter on grade, not sub-grade. That's pretty coarse risk bins. I guess it's possible to create a model better than LC's given the data we have or can get, but I don't see large obvious factors persisting over time.

Nonetheless filtering is widely practiced and by all accounts appears to work. What am I missing here? (Please avoid using the word heretic; also dummy if possible)

Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Randawl on January 12, 2014, 01:50:14 PM
Been thinking of writing this a while and have an hour or so before football. Folio users may ignore this thread. That's an entirely different animal.

Before we see any loan LC has reviewed it in sufficient depth to its own satisfaction to assign an interest rate sub-grade. Not only do they have all data that is eventually available to us in the browsenotes but, given direct access to the borrower, they clearly have much more. They have a team of seasoned professionals that lead the underwriting process and they have been doing this a long time. They have developed a proprietary loan scoring model and every bit of historic loan data available to us is also available to them. They have access to expensive historic data from the credit bureaus likely not economic for the rest of us to obtain. Finally, history has shown LC has done a pretty good job of achieving its goal to "... provide higher risk-adjusted returns for each loan grade increment from A1 to G5." (actually not so well with D, F and G).

LC policy makers select an interest rate structure that they feel will maximize their fees at any point in time, and loans are uniformly underwritten to conform to that structure. All loans graded XX on any day are to the very best of LC's ability the same and no loans are improperly graded XX when they should be YY.

So why is it that we believe we can use a subset of the data available to LC, filter for zero inquiries, no business loans, income >$3k/mo., etc. and get the "best" notes? Typically when we filter we filter on grade, not sub-grade. That's pretty coarse risk bins. I guess it's possible to create a model better than LC's given the data we have or can get, but I don't see large obvious factors persisting over time.

Nonetheless filtering is widely practiced and by all accounts appears to work. What am I missing here? (Please avoid using the word heretic; also dummy if possible)

I want to first address the above bolded phrase.  While it may be their theoretical intention to do so (and they have recently gotten better at it), it is not the case in our current reality.  That's how you make more money than the other person.  Take a look at the average account return curves.  The vast majority of people fall between 5%-10%.  What separates them?  Do you purport people's accounts above that 10% line are there 100% due to luck and no other factors?  Taking advantage of small inefficiencies and information asymmetries (even as they themselves change) is what keeps me multiple standard deviations above the crowd.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Lovinglifestyle on January 12, 2014, 02:03:40 PM
I hope somebody better qualified than I (who am not at all qualified) responds regarding the origination fee motivation factor discussed in other threads. 

If LC comes out ahead on loans that go bad, but investors come out behind, that would be grounds for suspicion regarding whose best interests are in mind when grading loans.  I believe in creating the highest good for all concerned (win-win), but the corporation has to look after its own bottom line first for anybody to win.  To what extent it does that may be where filtering has an edge.

Sorry for stating some of the obvious here.  Don't mean to waste your time.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Rob L on January 12, 2014, 03:04:18 PM
Taking advantage of small inefficiencies and information asymmetries (even as they themselves change) is what keeps me multiple standard deviations above the crowd.

I tried to make it clear at the beginning that Folio trading is a different animal completely. I'm talking about the purchase of fresh notes only. If Folio trading is part of your strategy my long winded post doesn't apply to you.

Only yesterday on another thread you mentioned Folio trading is part of your strategy and I certainly agree skilled traders have the edge there. Apparently you are one.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: core on January 12, 2014, 03:08:55 PM
I tried to make it clear at the beginning that Folio trading is a different animal completely. I'm talking about the purchase of fresh notes only. If Folio trading is part of your strategy my long winded post doesn't apply to you.

I don't know... he did say "multiple standard deviations above the crowd".  He couldn't have been talking about Folio because LC doesn't include Folio users on their pretty scatter plots.  So how would he know if he was multiple SDs above the crowd or not?  My conclusion:  He must have been talking about something else, on topic.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Ran on January 12, 2014, 03:34:45 PM
Been thinking of writing this a while and have an hour or so before football. Folio users may ignore this thread. That's an entirely different animal.

Before we see any loan LC has reviewed it in sufficient depth to its own satisfaction to assign an interest rate sub-grade. Not only do they have all data that is eventually available to us in the browsenotes but, given direct access to the borrower, they clearly have much more. They have a team of seasoned professionals that lead the underwriting process and they have been doing this a long time. They have developed a proprietary loan scoring model and every bit of historic loan data available to us is also available to them. They have access to expensive historic data from the credit bureaus likely not economic for the rest of us to obtain. Finally, history has shown LC has done a pretty good job of achieving its goal to "... provide higher risk-adjusted returns for each loan grade increment from A1 to G5." (actually not so well with D, F and G).

LC policy makers select an interest rate structure that they feel will maximize their fees at any point in time, and loans are uniformly underwritten to conform to that structure. All loans graded XX on any day are to the very best of LC's ability the same and no loans are improperly graded XX when they should be YY.

So why is it that we believe we can use a subset of the data available to LC, filter for zero inquiries, no business loans, income >$3k/mo., etc. and get the "best" notes? Typically when we filter we filter on grade, not sub-grade. That's pretty coarse risk bins. I guess it's possible to create a model better than LC's given the data we have or can get, but I don't see large obvious factors persisting over time.

Nonetheless filtering is widely practiced and by all accounts appears to work. What am I missing here? (Please avoid using the word heretic; also dummy if possible)

My take is that mass market always beat single authority. Individual market participant may not do a better job overall compared to LC scoring system, however, for a specific sector, for example, D notes, 60-month notes, some specialized market participant can develop a better model. And if that specialized market participant uses his own model for a sub-set of loans, while using LC for other notes, he will gain advantage. We have seen how LC have assigned higher rates for C/D but lower rates for 60m notes in the past years. Also LC as a company, even they noticed some deficiencies in their system, it takes time for them to react. If a few specialized scoring system providers like IR can cooperate to integrate their system, they can be even stronger.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: bobeubanks on January 12, 2014, 03:48:07 PM
I don't see how LC (or Prosper) has much motivation to truly assign interest rates in anything other than being more or less right. They get the origination fee up front, and then get about the same amount of extra income after that regardless of interest rate.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Rob L on January 12, 2014, 03:49:33 PM
I hope somebody better qualified than I (who am not at all qualified) responds regarding the origination fee motivation factor discussed in other threads.

Well I'll admit I'm pretty clueless about LC's motivations and policies too. However my understanding is that they do set the rates for all the loans, not just those for us small retail folks. Along with the rate they set comes an expected default rate. Institutional lenders are going to hold LC accountable to that default rate prediction and judge LC in no small measure on its accuracy as their portfolios mature. Seems to me that gives LC motivation to get it right, but that's just my uninformed working theory.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Randawl on January 12, 2014, 03:56:59 PM
Taking advantage of small inefficiencies and information asymmetries (even as they themselves change) is what keeps me multiple standard deviations above the crowd.
I tried to make it clear at the beginning that Folio trading is a different animal completely. I'm talking about the purchase of fresh notes only. If Folio trading is part of your strategy my long winded post doesn't apply to you.

That was clear indeed.  I, too, am talking about portfolio performance of a pure "filter and hold" strategy.  The inefficiencies to which I refer (in part) are regarding LC's imperfect underwriting model.  Not to imply that it should be perfect nor ever could be.  I say show me one that is perfect and I'll start the world's first infallible banking system.

Quote
Only yesterday on another thread you mentioned Folio trading is part of your strategy and I certainly agree skilled traders have the edge there. Apparently you are one.

Yes, I do use Folio, and I also know that when I separately analyze my trading and non-trading portfolios, my aforementioned statements remain true. 
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Rob L on January 12, 2014, 04:16:17 PM
We have seen how LC have assigned higher rates for C/D but lower rates for 60m notes in the past years. Also LC as a company, even they noticed some deficiencies in their system, it takes time for them to react.

Sure, that's why I said it was hard to see large obvious factors persisting over time. The LC model gets better, macro economic factors change, etc. If you believe personal filtering is essentially front-running the LC model by including relevant factors more quickly I guess that's a possibility.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Fred on January 13, 2014, 01:19:39 AM
What am I missing here?

For one, if we take LC's grades vs. FICO scores, LC's definition of "best note" is very different than that of FICO's.

Borrowers with FICO 700 have been assigned grades A to G by LC.  On the other hand, LC's grade A borrowers have shown FICO ranging from 660 to 845.

As an investor, I definitely make a distinction between grade A borrower with FICO 660 vs. grade A borrower with FICO 845.

You can see some data in this thread (http://www.lendacademy.com/forum/index.php?topic=1887.msg15772#msg15772).
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Rob L on January 13, 2014, 10:09:45 AM
For one, if we take LC's grades vs. FICO scores, LC's definition of "best note" is very different than that of FICO's.
Most certainly true. In their 2012 Goldman Conference briefing LC published a Gains chart claiming the KS scoring of their proprietary model was superior to FICO08. Believe it or not over time I don't know, but it certainly must have been true for the set of loans tested (Q2-Q4 2010).

I wonder if LC's model incorporates FICO as a parameter? My guess is that they do not, but they do incorporate the same borrower information used to create the FICO score. Even more I wonder why the two models diverge so greatly as shown in the numbers you referred to. What FICO 705 borrower's information makes the LC model assign a loan grade F or G? Do we have access to that same information in browsenotes, or more importantly do we have access in browsenotes to all the information LC uses in their model? I've never seen this question asked or answered, but as you may suspect my guess is no.

https://s3.amazonaws.com/lcmedia2.lendingclub.com/2012-Goldman-Conference.pdf
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Rob L on January 13, 2014, 11:27:54 AM
LC policy makers select an interest rate structure that they feel will maximize their fees at any point in time, and loans are uniformly underwritten to conform to that structure. All loans graded XX on any day are to the very best of LC's ability the same and no loans are improperly graded XX when they should be YY.

Sorry: to correct myself, "all loans graded XX on any day are the same". Not true.
The LC model scores of sub-grade XX loans will vary and some will be better than others. However they all fall within the XX "bin" so to speak, but no loans are assigned XX when they should be YY.
For example, E3 loans have various "best-ness" but no E3 loan is improperly graded as E2 or higher, nor E4 or lower (to the accuracy of the LC model).
We do have the opportunity to select the best E3's (or whatever) loans.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Emmanuel on January 13, 2014, 12:12:31 PM
The loan issuer may want to optimize its model for consistency, not absolute returns. If LC goal is to lower the 'risk' (risk being defined as discrepancies in default rates), they may cluster together loans with different expected returns. For instance, if loans A, B, and C have the following properties: default risk 5% +/- 2%, 7% +/- 5%, 13% +/- 2%, Lending Club could cluster B and C together, and then investors focusing on returns only will consider B a bargain, because it has the same interest rate than C which a much lower (average) default risk.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: rawraw on January 13, 2014, 03:04:51 PM
For one, if we take LC's grades vs. FICO scores, LC's definition of "best note" is very different than that of FICO's.
Most certainly true. In their 2012 Goldman Conference briefing LC published a Gains chart claiming the KS scoring of their proprietary model was superior to FICO08. Believe it or not over time I don't know, but it certainly must have been true for the set of loans tested (Q2-Q4 2010).


No they use FICO.  But they have info FICO doesn't have (income related).  So you'd expect it to be better.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Rob L on January 13, 2014, 06:01:13 PM
The loan issuer may want to optimize its model for consistency, not absolute returns.
Outstanding. LC certainly has every incentive to do just that and, if true, would explain my confusedness.
Maybe your posit isn't true.  Could be some other divergence between my goals and theirs but I'm a much happier camper now.
Thanks!

Note: Spell checker is cool with the word confusedness. Guess there's enough of us around to put it into the dictionary.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Dennis on January 13, 2014, 07:21:16 PM
Rob, you post a great question with this topic, one that has me really thinking.  I haven't been on these boards for about 2 months now because the posts were becoming way too social and not very informative.  But now you pose this great question....

I admit I'm one of those "best notes" people, in that I have my own criteria or "subset" as you put it, in choosing notes.  The challenge then, for me, is to beat the averages which I have consistently done for 2 1/2 years now.  This is a hobby for me, so I've mostly enjoyed the note selection process and I still do most of it manually.  I have been using filters at LC somewhat the last several months though as it has become increasing difficult to get those "best" notes if you're not fast enough.  But I use no filters at Prosper, and still hand pick (after using a general filter) all my notes at LC.

So personally I do think there is a subset within note grades (that's just my opinion) that can outperform the average in that grade.  I have nowhere near the skill set of many here who can run numbers, accurately configure probabilities, or create API's or other software, but I still do okay.

I have 3 P2P accounts, and even with the many defaults I get because of my high risk exposure, my current combined weighted average return for those accounts is currently 14.72%.  I've hovered around 15% for the last year and am currently at about the lowest return rate I've been at in 2 1/2 years.  The first notes I purchased will start paying off in the next 6 months (for those that go full term), and my 3 year experiment with P2P should yield some interesting results.  I am impressed with it so far.

Maybe I've been lucky, maybe I've stumbled on some skillset I don't know I have yet, or who knows what, but I will continue doing what I'm doing as long as I continue to get these results, which means that I believe there is a subset of notes that will outperform the averages. 

All that said, I don't like all the defaults I get, I hate when borrowers make less than 10 payments, and in some cases they make only 1 or 2 payments and then pay off the note - those things waste my time and frustrate me, but I've learned that it's just part of the game and you have to accept it.

Again, great question........

     
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Rob L on January 13, 2014, 08:39:58 PM
Rob, you post a great question with this topic, one that has me really thinking.  I haven't been on these boards for about 2 months now because the posts were becoming way to social and not very informative.  But now you pose this great question....   
Welcome back Dennis. My problem was a conundrum. From all evidence it appeared as if best loan selection was possible and a universally believed truism. I just didn't see how that could be, though I conceded it probably was.

Emmanuel's post was a real eye opener. The goals of LC's model and my personal investment goals are just not the same. It's obvious in hindsight but that hadn't occurred to me. Duh.. Where they diverge in my flavor I (we) have the opportunity tho select better notes.

I don't pretend to understand this very well, but I'm much more comfortable now with the possibility (reality) that better note selection is possible. The good news is that you're probably not just lucky but you're doing something right.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Randawl on January 13, 2014, 09:52:06 PM
Quote
From all evidence it appeared as if best loan selection was possible and a universally believed truism. I just didn't see how that could be, though I conceded it probably was.

I don't believe it's a universal truism that the "best" notes are always known ahead of time nor that the ones fully invested quickest are the "best."  Filtering is a double-edged sword and algo's/machine learning is imperfect as well.  They are useful tools but often over relied upon.

Quote
The goals of LC's model and my personal investment goals are just not the same.

That's often what we fall back on when we try to figure out why LC made another incongruent move.      ;)
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Dennis on January 13, 2014, 10:28:16 PM
Emmanuel's post was a real eye opener. The goals of LC's model and my personal investment goals are just not the same. It's obvious in hindsight but that hadn't occurred to me. Duh.. Where they diverge in my flavor I (we) have the opportunity tho select better notes.

The really great thing about this board is that it allows the convergence of thought from many different points of view.  Sometimes what's right in front of you will lay hidden until someone coming from a different angle sheds light on it.  I've been oblivious to the obvious so many times in my life that I stopped counting.  It doesn't mean I'm stupid, only that I was looking at something from the wrong angle.  This board has helped me so many times........     
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Fred on January 13, 2014, 10:52:56 PM
We do have the opportunity to select the best E3's (or whatever) loans.

Looks like you found an answer to your question. :)
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: rawraw on January 14, 2014, 07:58:15 AM
Rob, you post a great question with this topic, one that has me really thinking.  I haven't been on these boards for about 2 months now because the posts were becoming way too social and not very informative.  But now you pose this great question....

I admit I'm one of those "best notes" people, in that I have my own criteria or "subset" as you put it, in choosing notes.  The challenge then, for me, is to beat the averages which I have consistently done for 2 1/2 years now.  This is a hobby for me, so I've mostly enjoyed the note selection process and I still do most of it manually.  I have been using filters at LC somewhat the last several months though as it has become increasing difficult to get those "best" notes if you're not fast enough.  But I use no filters at Prosper, and still hand pick (after using a general filter) all my notes at LC.

So personally I do think there is a subset within note grades (that's just my opinion) that can outperform the average in that grade.  I have nowhere near the skill set of many here who can run numbers, accurately configure probabilities, or create API's or other software, but I still do okay.

I have 3 P2P accounts, and even with the many defaults I get because of my high risk exposure, my current combined weighted average return for those accounts is currently 14.72%.  I've hovered around 15% for the last year and am currently at about the lowest return rate I've been at in 2 1/2 years.  The first notes I purchased will start paying off in the next 6 months (for those that go full term), and my 3 year experiment with P2P should yield some interesting results.  I am impressed with it so far.

Maybe I've been lucky, maybe I've stumbled on some skillset I don't know I have yet, or who knows what, but I will continue doing what I'm doing as long as I continue to get these results, which means that I believe there is a subset of notes that will outperform the averages. 

All that said, I don't like all the defaults I get, I hate when borrowers make less than 10 payments, and in some cases they make only 1 or 2 payments and then pay off the note - those things waste my time and frustrate me, but I've learned that it's just part of the game and you have to accept it.

Again, great question........

   
Are you continually adding new money?  If so, this could keep your returns high for a bit until the average age increases.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Rob L on January 14, 2014, 10:11:25 AM
Are you continually adding new money?  If so, this could keep your returns high for a bit until the average age increases.
No, I'm not even re-investing payments received; just letting all my notes run off. My question wasn't prompted by poor performance and I understand your comment regarding the returns of young notes. My account's about 6 months old and doing fine (though not multiple sigmas above the curve). My question was spurred simply by a fundamental lack of understanding of "why", and the possible similarity of arguments for and against technical analysis of stocks, random walk, etc.

My account is traditional IRA. When LC changed the rules after I joined to prohibit my use of Folio I was robbed of the option to liquidate my account if I chose.
LC has said they plan to address this in the future, but it isn't a priority. Until they do I'll continue to let the account run off and invest the dollars returned  elsewhere.

I am planning to open a non-IRA account and basically start over. For me it's an interesting, enjoyable and profitable hobby so I plan to stay in the game.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: dontvote on January 14, 2014, 12:50:31 PM
Evaluating credit like this seems more like fundamental stock analysis than technical stock analysis. I would consider the analogy of picking notes out of LC's credit model being more like analyst rankings at your brokerage. With a bit of judgement and significant diligent effort, you can probably do better than the analyst (or at least pick a subset of his picks that fit with your investment scheme).  You can apply two different models to the same data and get very different results. The model doesn't have to be filter results based or algorithmic, it's just a framework you can test.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Emmanuel on January 14, 2014, 12:52:30 PM
Emmanuel's post was a real eye opener. The goals of LC's model and my personal investment goals are just not the same. It's obvious in hindsight but that hadn't occurred to me. Duh.. Where they diverge in my flavor I (we) have the opportunity tho select better notes.

You're too kind! That's one explanation, but keep in mind I may be totally wrong ;-)
In any case, we plan to do some serious statistical analysis in the near future, so hopefully it will bring a bit more light
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Dennis on January 14, 2014, 02:54:12 PM
Are you continually adding new money?  If so, this could keep your returns high for a bit until the average age increases.

rawraw, I think you were directing that question towards me: 

It's been about a year since I put any new money into any of my 3 accounts.  I personally have found it near impossible to add new money now that there's so much competition for notes.  I've been struggling to just keep up with reinvestment, but have fallen behind on that now, through the holidays.  I have a good deal of cash sitting in all my accounts presently.  So my portfolios therefore are pretty seasoned.  Like I said, I'm 2 1/2 years into this now, and my return is at about the lowest it's been in that time.  I currently hover around 15%, but it was much higher a year ago when many of my notes were newer as you suggest. 
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Bohb Daishi on January 14, 2014, 10:29:56 PM
I would consider the analogy of picking notes out of LC's credit model being more like analyst rankings at your brokerage. With a bit of judgement and significant diligent effort, you can probably do better than the analyst (or at least pick a subset of his picks that fit with your investment scheme).

It's not hard to beat analysts. In fact, most don't even know what the heck they are talking about. If they were smart enough to accurately predict where a stock would go, they would be fund managers. I've read many research notes and I can tell you, most of these guys have absolutely no idea what the company actually does. They have an even worse idea of how to value the company.

Remember, these are the same people who said the housing market would always go up, gold would always go up, subprime mortgages are "AAA", dotcom tech stocks would always go up, and that zero-revenue social media companies are worth billions of dollars.


What I'm trying to say is, there are always going to be very big arbitrage opportunities in "one size fits all" pricing models, like what LendingClub and stock analysts use.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Randawl on January 14, 2014, 10:32:21 PM
What I'm trying to say is, there are always going to be very big arbitrage opportunities in "one size fits all" pricing models, like what LendingClub and stock analysts use.

That's a great way to put it
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Joleran on January 15, 2014, 08:12:17 AM
It's not hard to beat analysts. In fact, most don't even know what the heck they are talking about. If they were smart enough to accurately predict where a stock would go, they would be fund managers.

If they can repeatedly and accurately pick where any stock or set of stocks would go, they would be billionaires.  The number of funds that have been able to produce any alpha whatsoever on a consistent basis for more than 10 years can be counted on one hand.

Think about it like this - how many funds underperform their index every year?  If you have a thousand funds and you assume it's completely random, you might expect 500 outperform the first year, of which 250 the second year, 125 the third year, 62 the fourth year, 31 the fifth year, 16 the sixth year, 8 the seventh year, 4 the eighth year, 2 the ninth year, and 1 the tenth year.  In reality though, 80% of fund managers on average underperform their index so the odds are worse.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Rob L on January 15, 2014, 06:11:20 PM
You're too kind! That's one explanation, but keep in mind I may be totally wrong ;-)
Of course your example may be wrong, but there are any number of other similar divergences of goals that are possible. I just didn't see that.
For the sake or argument lets say your argument is right. Does that mean some borrowers get better deals than others simply for the sake of consistency optimization?
The borrowers that get the bad deals relatively speaking are the loans we seek. Or, did I miss the point completely?
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: dontvote on January 16, 2014, 12:10:13 PM
You're too kind! That's one explanation, but keep in mind I may be totally wrong ;-)
Of course your example may be wrong, but there are any number of other similar divergences of goals that are possible. I just didn't see that.
For the sake or argument lets say your argument is right. Does that mean some borrowers get better deals than others simply for the sake of consistency optimization?
The borrowers that get the bad deals relatively speaking are the loans we seek. Or, did I miss the point completely?

You're exactly right. If risk were priced perfectly, everyone would have a custom interest rate and there would be very little difference between holding any loans across risk categories. Yes, some borrowers are 'overpaying' given their real risk parameters making them 'safer' than their interest rates. Those are the 'better' loans everyone seeks.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Rob L on January 19, 2014, 02:16:03 AM
I guess it's possible to create a model better than LC's given the data we have or can get, but I don't see large obvious factors persisting over time.

Think I found an example of this while poking around on IR.
Loans are 36 month only.

For all loan grades between 2008-10 and 2010-12:
Inquires       # of Loans             Average Interest Rate               Avg IRR
      0                    6512                              11.3%                                 5.9%
      1                    3771                              11.6%                                 4.3%
      2                    1990                              11.7%                                 4.4%
      3                    1126                              12.0%                                 0.7%

For all loan grades between 2010-12 and 2014-01:
Inquires       # of Loans             Average Interest Rate               Avg IRR
      0                   79836                             12.0%                                  6.6%
      1                   42979                             13.5%                                  6.8%
      2                   19727                             14.2%                                  6.1%
      3                    8866                              14.7%                                  4.8%

In the earlier sample set LC did not increase the borrowers interest rate in response to an increased number of inquires.  As a result the lenders IRR fell sharply as inquires increased. All of these loans have been fully paid or charged off.

In the second sample set it appears LC updated its model to recognize increased risk of default when inquires are >0 and charge the borrower a higher interest rate accordingly. Note that the IRR for inquires = 1 is actually > than inquires = 0 now.  At first blush it would appear that the LC model now fully compensates the lender for multiple inquires (at least 1-2) so filtering for inquires=0 is not helpful and possibly counterproductive. Most of these loans are not yet mature so all the IRR's are higher than the older set.

From a little reading it seems number of inquires has long been recognized as a significant consumer credit default risk factor. I have no idea why LC may have left it out or under weighted it in earlier models. Makes me think I've probably got it wrong since I have so little experience with this stuff.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Ran on January 19, 2014, 10:35:13 AM
It's not hard to beat analysts. In fact, most don't even know what the heck they are talking about. If they were smart enough to accurately predict where a stock would go, they would be fund managers.

If they can repeatedly and accurately pick where any stock or set of stocks would go, they would be billionaires.  The number of funds that have been able to produce any alpha whatsoever on a consistent basis for more than 10 years can be counted on one hand.

Think about it like this - how many funds underperform their index every year?  If you have a thousand funds and you assume it's completely random, you might expect 500 outperform the first year, of which 250 the second year, 125 the third year, 62 the fourth year, 31 the fifth year, 16 the sixth year, 8 the seventh year, 4 the eighth year, 2 the ninth year, and 1 the tenth year.  In reality though, 80% of fund managers on average underperform their index so the odds are worse.

You are missing a point there. It's true that funds generally underperform the market in the long run. However, we are talking about "market" here. In LC's case, LC is not THE market, and they are a better competitor in the best case. So LC is expected to underperform THE market and in some sectors of loans, one can expect some market participants to beat LC.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Randawl on January 19, 2014, 11:00:38 AM
I guess it's possible to create a model better than LC's given the data we have or can get, but I don't see large obvious factors persisting over time.

Think I found an example of this while poking around on IR.
Loans are 36 month only.

For all loan grades between 2008-10 and 2010-12:
Inquires       # of Loans             Average Interest Rate               Avg IRR
      0                    6512                              11.3%                                 5.9%
      1                    3771                              11.6%                                 4.3%
      2                    1990                              11.7%                                 4.4%
      3                    1126                              12.0%                                 0.7%

For all loan grades between 2010-12 and 2014-01:
Inquires       # of Loans             Average Interest Rate               Avg IRR
      0                   79836                             12.0%                                  6.6%
      1                   42979                             13.5%                                  6.8%
      2                   19727                             14.2%                                  6.1%
      3                    8866                              14.7%                                  4.8%

In the earlier sample set LC did not increase the borrowers interest rate in response to an increased number of inquires.  As a result the lenders IRR fell sharply as inquires increased. All of these loans have been fully paid or charged off.

In the second sample set it appears LC updated its model to recognize increased risk of default when inquires are >0 and charge the borrower a higher interest rate accordingly. Note that the IRR for inquires = 1 is actually > than inquires = 0 now.  At first blush it would appear that the LC model now fully compensates the lender for multiple inquires (at least 1-2) so filtering for inquires=0 is not helpful and possibly counterproductive. Most of these loans are not yet mature so all the IRR's are higher than the older set.

From a little reading it seems number of inquires has long been recognized as a significant consumer credit default risk factor. I have no idea why LC may have left it out or under weighted it in earlier models. Makes me think I've probably got it wrong since I have so little experience with this stuff.

Interesting data.  Just wanted to point out, FYI, that because no loss factor is included with the calculation of the second data set (and since they're so young, the riskier ones appear more inflated than others), those with increasing inquiries may or may not have had enough time to differentiate themselves and increase their default rates as they age.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Rob L on January 19, 2014, 12:21:00 PM
Interesting data.  Just wanted to point out, FYI, that because no loss factor is included with the calculation of the second data set (and since they're so young, the riskier ones appear more inflated than others), those with increasing inquiries may or may not have had enough time to differentiate themselves and increase their default rates as they age.

Quite true, we certainly don't know how the newer loans will eventually turn out. What we do know is that LC now appears to increase interest rates at loan initiation based on increasing number of inquires whereas in the past it appears they did not. However, the updated LC model (if that's what this is) may now still be under compensating or over compensating for inquires at loan initiation. We'll know that answer in a couple of years.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Rob L on January 19, 2014, 02:34:42 PM
Borrowers with FICO 700 have been assigned grades A to G by LC.

Here's an extreme example. FICO at origination 770-774 yet LC assigned loan grade F2 (24.08%). Also the IR01 score is Poor.
The LC and IR models knew this one was a much riskier bet than the high FICO score indicated.

https://www.lendingclub.com/account/loanPerf.action?loan_id=7044744&order_id=10971049&note_id=29848844 (https://www.lendingclub.com/account/loanPerf.action?loan_id=7044744&order_id=10971049&note_id=29848844)

And they were right. Two months into the loan, the borrower has stopped paying and the loan has been sent off to external collections.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: neals384 on January 20, 2014, 09:55:30 AM
LC has no incentive to price every loan at the "perfect" interest rate.  Almost all of their listings fill anyway.

Lenders has a financial incentive to select notes with the most attractive interest rate given the known risks.

People and organizations with financial incentives, talent and the willingness to work hard (Lend Academy folks) will almost always outperform those with no incentive (LC).

Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Emmanuel on January 20, 2014, 01:46:28 PM
LC has no incentive to price every loan at the "perfect" interest rate.  Almost all of their listings fill anyway.

Lenders has a financial incentive to select notes with the most attractive interest rate given the known risks.

People and organizations with financial incentives, talent and the willingness to work hard (Lend Academy folks) will almost always outperform those with no incentive (LC).

I respectfully disagree... It is in LC or Prosper's interest to price their loans as well as possible. First, for the sake of market efficiency and avoiding supply/demand unbalance. Second, because of their financial incentives. They need to be borrower-friendly because of the originating fees they get when issuing new loans (too expensive = less demand), and lender-friendly because a) that's where the money is coming from and b) they get 1% of service fees on the payments (too cheap = less supply, and less service fees).

The hardest thing when investing in the Stock Market is sorting out signal from noise, because the amount of information is almost infinite. Therefore the value of investment advisers / analyst / gurus come for picking which data to focus on. In Peer Lending, there are relatively few data available (about 100 data fields in LC loans' history), so finding solutions is relatively easy and attainable with several well-know optimization algorithms. Even a brute-force simulation would probably work.

Something LC could easily do, even more so since they have more data than us (for instance, they could use the identify of the borrower to establish his 'social' credentials, grade his job situation based on his LinkedIn profile, assess its worth or lifestyle based on his FB posts). And I still have to meet a LC employee who seems stupid or lazy. So, even smart and dedicated Lend Academy members are unlikely to 'beat' them. Unless 'perfect' means different things for LC and for us. Thinking about it, it should be possible to 'find' what they're optimizing for based on their historical data.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: quantalcontent on January 22, 2014, 11:05:23 PM
In Peer Lending, there are relatively few data available (about 100 data fields in LC loans' history), so finding solutions is relatively easy and attainable with several well-know optimization algorithms. Even a brute-force simulation would probably work.

So here's an observation (and a question) from someone contemplating getting started with investing. Over time, LC changes their underwriting criteria and rate-setting algorithm, perhaps frequently. Not only do they not tell us what these criteria and algorithms are, they also don't tell us when they change them. So, if you use historical data to classify notes, you run the risk of making serious errors. Yet, this is exactly what many third-party note-picking services seem to do.

The example provided by Rob L shows just what I mean. I had hit on the same observation. After playing around with LC's data for 36 month loans completed by 2013, I thought I was a genius: all you have to do is get rid of borrowers who made more than 0 inquiries, and you'll easily reduce your defaults even on C, D and higher loans! But it seems that LC might have caught onto this and changed the influence of inquiries on interest rate. All those note-picking services use algorithms more complicated than my "avoid inquiries" algorithm, but the problem is exactly the same: LC could be pulling the rug out from under them and investors wouldn't know it for years.

I'm curious about what the denizens of this forum think about this concern. Am I missing something? How likely is it that "picking the best notes" today based on yesterday's data will prove to be counterproductive?
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: brycemason on January 23, 2014, 09:52:58 AM
You are missing something. Incorporate the interest rate into your selection of notes. Then if LC changes it, so too will your selection of notes. If LC today made a stray "A" note with 40% interest, it would automatically be at the top of my profit max list.

The past is the absolute best thing we have to predict the future. I imagine LC set their initial risk model with personal loan data from some other market, and then has updated it as their own loans matured. How else are you imagining they set interest rates besides historically consistent relationships between borrower characteristics and the probability of default?
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: quantalcontent on January 23, 2014, 12:33:49 PM
I'm not sure what you mean by "incorporate interest rate". I did that by making a simple logistic regression model to predict default rates, using all the data for completed 36 month loans through 2013. I included a few parameters that seemed to contribute substantially to the variance; one of the best predictors was "inquiries in the last 6 months". I also included "interest rate" and a few others. So then I had a regression equation that let me determine the probability that any given loan would default. Of course it works well for the historical data (because that's what the model is based on). If LC recently bumped up the interest rate for borrowers with a high number of inquiries, the model might still work roughly OK because it includes interest rate as one of the predictors. (Although using "category", i.e., A1-G5, as a predictor actually works better than interest rate, presumably because it's not subject to the variability in interest rates that LC introduces by responding to market pressure.)

HOWEVER, this does not take into account the possibility that LC actually changed their underwriting for loans with higher inquiries. Suppose they rejected more of them unless the borrower met other requirements, such as having a higher income, lower DTI, or some other as yet non-transparent factor. Then the influence of inquiries on default rate would be fundamentally different today than it was in the last few years (because the population sampled by LC is now different: they are accepting and rejecting a different group of borrowers with different characteristics, among which "inquiries" is no longer strongly related to default rate), and the model would overpredict default rates. I'd be hurting myself by using "inquiries" as a criterion for rejecting notes.

So, while I completely agree with you that historical data is the best way to predict the future, those predictions assume some consistency between the past and the present. Because LC periodically changes its underwriting and rate-setting alrgorithms, there is less consistency - perhaps a lot less. So predictions are less valid, meaning that the risk of using them is greater.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: dontvote on January 23, 2014, 01:37:08 PM
It's a tautology - the only data is the best data. The past is the only information we have to predict the future but while statistical methods can help shed light on some possible fundamental relationships, they are not able to show them explicitly.

I don't think anyone would disagree that the limited fields we have avail are mere proxies for what is actually going on in people's lives.

dontlietomedamnrobot
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Emmanuel on January 23, 2014, 03:37:46 PM
So here's an observation (and a question) from someone contemplating getting started with investing. Over time, LC changes their underwriting criteria and rate-setting algorithm, perhaps frequently. Not only do they not tell us what these criteria and algorithms are, they also don't tell us when they change them. So, if you use historical data to classify notes, you run the risk of making serious errors. Yet, this is exactly what many third-party note-picking services seem to do.

A way around that is to estimate the default probability based on all criteria BUT the grade/interest rate. That gives you an interest rate to be at equilibrium, and you deduct it from the grade/interest determined by LC. The higher the value, the better the bargain.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: edward on January 23, 2014, 05:46:02 PM
For those of you with a credit granting background, does LC see the FICO history when they run an inquiry or just the snapshot at that moment in time? In your experience, would it make any difference if they did--that is, how predictive is past FICO of future repayment likelihood?
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: brycemason on January 23, 2014, 07:46:07 PM
So here's an observation (and a question) from someone contemplating getting started with investing. Over time, LC changes their underwriting criteria and rate-setting algorithm, perhaps frequently. Not only do they not tell us what these criteria and algorithms are, they also don't tell us when they change them. So, if you use historical data to classify notes, you run the risk of making serious errors. Yet, this is exactly what many third-party note-picking services seem to do.

A way around that is to estimate the default probability based on all criteria BUT the grade/interest rate. That gives you an interest rate to be at equilibrium, and you deduct it from the grade/interest determined by LC. The higher the value, the better the bargain.

Winner winner, chicken dinner.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Fred on January 24, 2014, 01:59:14 AM
For those of you with a credit granting background, does LC see the FICO history when they run an inquiry or just the snapshot at that moment in time?

Most places that I have worked in only dealt with the latest FICO score.  Some took the 3 scores from different credit reporting agencies, and then took the average, min or max, of them.  However, I have never been a position where historical FICO scores were considered during underwriting.

On the other hand, historical (usually past 2 years) income and employment are often considered.

I have not been in a consumer finance underwriting role since 2007, so things might have changed since then.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Rob L on January 28, 2014, 06:10:52 PM
In the interest of continuity I'm repeating this post from another thread which was in response to Simon's blog article. It is very on topic here.
http://www.lendingmemo.com/redlining-florida-lending-club-prosper/ (http://www.lendingmemo.com/redlining-florida-lending-club-prosper/)
http://www.lendacademy.com/forum/index.php?topic=2000.0 (http://www.lendacademy.com/forum/index.php?topic=2000.0)

Making loans to Florida is only a bad bet if LC has set the interest rate too low.
From the discussion in this thread it appears that, early on, the LC model did not weight # inquires heavily enough and lenders were under compensated. Over time it appears LC recognized this and updated their model. I wondered if the same had happened for the state of Florida parameter.

Using Interest Radar I found the following (only 36 month term loans included):

                   All Grade  Loans                                A,B Only Loans
Year   # Loans    Int Rate    FL Int Rate        # Loans    Int Rate    FL Int Rate
2009    4716        12.2%        12.2%             2543         10.3%       10.2%
2010    8466        11.1%        11.1%             5217           9.0%         9.0%
2011  14101        10.6%        10.5%            10301           8.9%         8.9%
2012  43470        12.6%        12.6%            27558         10.4%       10.4%
2013  97776        13.4%        13.6%            55971         10.6%       10.7%

Each year FL loans were between 6.7% and 7.3% of total originations.

It seems pretty clear that, unlike # inquires, LC has not learned from history and has not increased interest rates for Florida borrowers. Simon is right. By all appearances filtering by state works and Florida likely remains a bad bet.

Could be that the law (or the possibility of negative publicity) precludes consideration of such redlining or hot button factors by LC in their model. There's a story I read about one lender that used the number of vowels in the borrower's last name to filter for ethnicity. The word got out and there were very serious repercussions. If memory serves it cost them their business.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: RaymondG on January 28, 2014, 11:54:48 PM
I just realized that I have a large amount of loans from CA, FL and NV. But the lose from these loans are average or better which might be because I use a little more restrict criteria to pick loans from these three states.

[attachment deleted by admin]
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Bohb Daishi on January 29, 2014, 02:59:07 AM
Could be that the law (or the possibility of negative publicity) precludes consideration of such redlining or hot button factors by LC in their model. There's a story I read about one lender that used the number of vowels in the borrower's last name to filter for ethnicity. The word got out and there were very serious repercussions. If memory serves it cost them their business.

Look at the bottom right of their home page where it says "Equal Housing Lender". That typically means they can't "discriminate" by illegal factors such as location.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Rob L on February 02, 2014, 06:32:31 PM
A natural question to ask is "How accurate has LC's model been over the years".

For each loan in the browsenotes file LC provides its sub-grade which is defined by "interest rate" and "expected default rate" (both provided).
Terrific; all I have to do is go back to the LoanStats files, pull the expected default rates over the periods used (LC updates these along with interest rates periodically), and see how well LC did.

As I'm sure it's well known to folks that have been here much longer than I, LC doesn't record in LoanStats the expected default rate they provided at the time of loan issuance. See:

http://www.lendacademy.com/forum/index.php?topic=560.msg1916#msg1916 (http://www.lendacademy.com/forum/index.php?topic=560.msg1916#msg1916)

Very convenient. Looks like LC must not want folks going back to see how well their predictions held up.
The only way to have the required data is to have recorded and preserved one or more browsenotes files during each of the periods of sub grade use.
My browsenotes records only go back to 05/13. Not much help. Any old timers out there have the long record?

Superbowl time!
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Emmanuel on February 03, 2014, 10:52:52 AM
A natural question to ask is "How accurate has LC's model been over the years".

For each loan in the browsenotes file LC provides its sub-grade which is defined by "interest rate" and "expected default rate" (both provided).

I far as I know, default risk determines the grade, then grade + term determines the interest rate. Therefore to gauge LC's accuracy, one can simply check the correlation between sub-grades and default rates, see https://lendingrobot.com/data#default_sub (https://lendingrobot.com/data#default_sub).

As one can see, LC does a pretty good job with higher quality loans, not so much when the risks increases, which makes sense since there are more outliers.


Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Rob L on February 03, 2014, 02:43:43 PM
I far as I know, default risk determines the grade, then grade + term determines the interest rate.
Therefore to gauge LC's accuracy, one can simply check the correlation between sub-grades and default rates, see https://lendingrobot.com/data#default_sub (https://lendingrobot.com/data#default_sub).

Yes that should do it. One could even make similar charts by vintage if so inclined. We could see if LC is getting any better at it over time.
It would also be interesting to have a similar graph of FICO range at application vs. default rate for comparison.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: dontvote on February 04, 2014, 05:16:39 PM
The best indication that their credit model is working accurately is a sameness between captured returns across the grades. b-g should basically give you the same return if you buy all the notes offered. This is the fully diversified naive portfolio that shows how well they are pricing risk to give an after default economic return for the platform. I think they've been doing a pretty darn good job. B-G are basically giving you about the same.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Beekaycee on February 04, 2014, 09:12:52 PM
The best indication that their credit model is working accurately is a sameness between captured returns across the grades. b-g should basically give you the same return if you buy all the notes offered. This is the fully diversified naive portfolio that shows how well they are pricing risk to give an after default economic return for the platform. I think they've been doing a pretty darn good job. B-G are basically giving you about the same.

With tax filing season top of mind it struck me that for those individuals with a taxable Lending Club account equal returns across the grades may give substantially unequal results after taxes.

We are fully taxed on the interest, but limited to $3000 capital losses per year from your defaults (unless you have other capital gains to offset). Any losses you can't deduct roll forward, but meanwhile the defaults keep coming in, too.

Bottom line, the high risk grades throw off big interest yields, but also have large defaults that you may not get to deduct anytime soon.



Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Rob L on February 04, 2014, 09:58:27 PM
The best indication that their credit model is working accurately is a sameness between captured returns across the grades. b-g should basically give you the same return if you buy all the notes offered. This is the fully diversified naive portfolio that shows how well they are pricing risk to give an after default economic return for the platform. I think they've been doing a pretty darn good job. B-G are basically giving you about the same.

I must be reading this paragraph from the LC "How We Set Rates" paragraph incorrectly:

Lending Club’s interest rates take into account credit risk and market conditions. The final interest rate for each loan grade is the result of the following equation:
Lending Club Base Rate + Adjustment for Risk & Volatility
The Adjustment for Risk & Volatility is designed to cover expected losses and provide higher risk-adjusted returns for each loan grade increment from A1 to G5.

Seems clear to me that says lenders should expect a higher return for riskier loans, not the same risk adjusted return across the board. That returns have been flat, as you correctly describe, says LC has done a lousy job of accomplishing their stated goal (from a lender's point of view).


Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: dontvote on February 05, 2014, 11:56:33 AM
What I'm calling the 'economic return' is the return net of defaults. That means that you will have a higher rate of defaults on higher interest rate loans. So yes investors get higher rates on riskier loans with higher default rates. If the system works well, your rate of return will be the same after all is said and done, irregardless of the loan grade you invest in.

this is describing the same principal that evens asset class returns. higher return assets get bid up until all returns from risky money are basically equivalent. It doesn't always work cleanly, but it is a basic market force that contributes to asset class prices.

in the p2p space we saw this early when people took a look at the 14% average returns from higher yield notes and said anyone investing in higher grade notes earning 11% after defaults was leaving money on the table.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Rob L on February 05, 2014, 04:01:23 PM
What I'm calling the 'economic return' is the return net of defaults. That means that you will have a higher rate of defaults on higher interest rate loans. So yes investors get higher rates on riskier loans with higher default rates.

Clearly true.

Quote
If the system works well, your rate of return will be the same after all is said and done, irregardless of the loan grade you invest in.

I just can't see that being correct for a number of reasons.

What you are saying is that the feeding time frenzy for the riskier notes by individual and institutional investors alike is a fool's errand. Just buy a fully diversified portfolio of B notes and fugetaboutit. No doubt everyone caught up in this frenzied buying believes they are getting the "best notes".

For the sake of agreement lets say LC successfully assigns interest rates so that the lender has no economic incentive to invest in riskier notes. Why would anyone do so? They hope they get lucky?

Consider loan grade diversification risk. If you want to build a fully diversified portfolio of A or B notes it's pretty easy. But as the grades become more risky the variance of returns of portfolios not containing every loan of that grade increases. If you have 100 A notes you are far more certain your portfolio returns will be near the average of all A notes than portfolio of 100 F notes being near the average of all F notes. It wasn't that long ago that LC had to stop claiming that no investor with 800+ notes had ever lost money. Someone did; and I'll bet that person wasn't holding A's and B's. I don't know the answer but it would be interesting to know over all fully matured F loans the required number of notes in your all F grade portfolio needed to have 95% confidence of being within 5% of the average of all F note returns.

Maybe my argument above is badly flawed, but it seems to me that if real returns after charge offs do not increase with risk (not just keep pace with it) then they are a bad bet.
However we see from the link below it's the bet LC investors have been making. So much money chasing yield ...

https://www.lendingrobot.com/data#by_sub (https://www.lendingrobot.com/data#return_sub)
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: dontvote on February 05, 2014, 06:04:38 PM
What I'm calling the 'economic return' is the return net of defaults. That means that you will have a higher rate of defaults on higher interest rate loans. So yes investors get higher rates on riskier loans with higher default rates.

Clearly true.

Quote
If the system works well, your rate of return will be the same after all is said and done, irregardless of the loan grade you invest in.

I just can't see that being correct for a number of reasons.

What you are saying is that the feeding time frenzy for the riskier notes by individual and institutional investors alike is a fool's errand. Just buy a fully diversified portfolio of B notes and fugetaboutit. No doubt everyone caught up in this frenzied buying believes they are getting the "best notes".

For the sake of agreement lets say LC successfully assigns interest rates so that the lender has no economic incentive to invest in riskier notes. Why would anyone do so? They hope they get lucky?

Consider loan grade diversification risk. If you want to build a fully diversified portfolio of A or B notes it's pretty easy. But as the grades become more risky the variance of returns of portfolios not containing every loan of that grade increases. If you have 100 A notes you are far more certain your portfolio returns will be near the average of all A notes than portfolio of 100 F notes being near the average of all F notes. It wasn't that long ago that LC had to stop claiming that no investor with 800+ notes had ever lost money. Someone did; and I'll bet that person wasn't holding A's and B's. I don't know the answer but it would be interesting to know over all fully matured F loans the required number of notes in your all F grade portfolio needed to have 95% confidence of being within 5% of the average of all F note returns.

Maybe my argument above is badly flawed, but it seems to me that if real returns after charge offs do not increase with risk (not just keep pace with it) then they are a bad bet.
However we see from the link below it's the bet LC investors have been making. So much money chasing yield ...

https://www.lendingrobot.com/data#return_sub (https://www.lendingrobot.com/data#return_sub)

what I'm saying is true in aggregate - you have to invest in every loan to have equivalent return across grades

if you feel that you can pick loans within the range better than 'all loans' your 'skill' will have more impact among higher yielding loans.

I will tell you without asking anyone else that people who are picking loans think they are going to beat the averages. people who pick people who are picking loans think the same.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Bohb Daishi on February 06, 2014, 02:04:56 AM
what I'm saying is true in aggregate - you have to invest in every loan to have equivalent return across grades

if you feel that you can pick loans within the range better than 'all loans' your 'skill' will have more impact among higher yielding loans.

I will tell you without asking anyone else that people who are picking loans think they are going to beat the averages. people who pick people who are picking loans think the same.

Even in aggregate, the risk/reward should never be the same across all loan grades. If you made the same amount of money investing in G5 notes as you would investing in A1, then everyone would put their money in A1 because they would prefer to not deal with defaults. The higher return is the compensation you receive for putting up with higher default rates. Some people want zero defaults, so they put all their money in low-risk grades. Likewise, some people aren't bothered by having defaults, so they put money in higher risk notes.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: dontvote on February 07, 2014, 02:30:45 PM
what I'm saying is true in aggregate - you have to invest in every loan to have equivalent return across grades

if you feel that you can pick loans within the range better than 'all loans' your 'skill' will have more impact among higher yielding loans.

I will tell you without asking anyone else that people who are picking loans think they are going to beat the averages. people who pick people who are picking loans think the same.

Even in aggregate, the risk/reward should never be the same across all loan grades. If you made the same amount of money investing in G5 notes as you would investing in A1, then everyone would put their money in A1 because they would prefer to not deal with defaults. The higher return is the compensation you receive for putting up with higher default rates. Some people want zero defaults, so they put all their money in low-risk grades. Likewise, some people aren't bothered by having defaults, so they put money in higher risk notes.

you're right, there is a volatility of return which is higher in the riskier notes that will give them some additional risk premia but that should be really small since we're looking at all loans in aggregate. while G loans may have a standard deviation of default rates that changes across time and that deviation will be larger than that of grade b loans I don't see why it would be a large amt.  Additionally, since a bad economy will ostensibly affect riskier notes more that should add to their return requirement (all else being equal).   I was trying to simplify to say we'll know if the models are working well if we see aggregate returns at *about* the same level. And we do outside of the lowest risk notes.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Rob L on February 08, 2014, 02:05:36 AM
you're right, there is a volatility of return which is higher in the riskier notes that will give them some additional risk premia but that should be really small since we're looking at all loans in aggregate. while G loans may have a standard deviation of default rates that changes across time and that deviation will be larger than that of grade b loans I don't see why it would be a large amt.  Additionally, since a bad economy will ostensibly affect riskier notes more that should add to their return requirement (all else being equal).   I was trying to simplify to say we'll know if the models are working well if we see aggregate returns at *about* the same level. And we do outside of the lowest risk notes.

I think you said investors holding a well diversified portfolio of riskier loans should expect higher real returns than those holding a well diversified portfolio of less risky ones. Riskiness defined as the probability of default (charge off). Our only difference of opinion appears to be the amount of additional returns the lender should expect. You say really small and LC doesn't say how much. I dunnow.

The Lending Robot "Returns by sub-grade" graph only included fully matured loans and there were only 142 F loans fully matured or paid off early.
The average interest rate was 18.5%. In 2013 LC issued 607 F grade loans at an average interest rate of 23.9%.

Using Interest Radar the Avg IRR for all loans issued in 2013 is:
A  6.2%
B  8.9%              +2.7%
C  11.6%           +2.7%
D  11.8%           +0.2%
E  12.6%           +0.8%
F  6.5%              -6.1% ***

It's very early yet, but the gain in return for holding riskier loans flattens from C forward, and crashes for F.
This F performance reflects that of the F notes in my own portfolio. I stopped buying F notes in early December. Don't know why anyone does.

Maybe the above numbers is what LC wants its model to do. Strongly reward risk to the C level, then reduce the incremental increases thereafter. I would have guessed the reverse. Except for the really bad F note problem I'll have to stand down from my "lousy job" comment. The rest could be just what they want.



Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Rob L on July 22, 2014, 10:35:32 AM
Just read the transcript of Peter's podcast with LC CEO Renaud Laplanche.
He remains rather outspoken in his opinion of this "best note selection business" and devotes a bit of time explaining his reasons.
http://www.lendacademy.com/lap20-renaud-laplanche-lending-club/ (http://www.lendacademy.com/lap20-renaud-laplanche-lending-club/)
There may still be pockets of inefficiency but they will continue to become fewer and harder to identify over time.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: turing on July 22, 2014, 12:36:41 PM
Just read the transcript of Peter's podcast with LC CEO Renaud Laplanche.
He remains rather outspoken in his opinion of this "best note selection business" and devotes a bit of time explaining his reasons.
http://www.lendacademy.com/lap20-renaud-laplanche-lending-club/ (http://www.lendacademy.com/lap20-renaud-laplanche-lending-club/)
There may still be pockets of inefficiency but they will continue to become fewer and harder to identify over time.

Always good to hear from the CEO and get glimpse into company policy.  That being said, everything needs to be taken with a grain of salt because it is PR speak and legal reasons he can't say things.

No matter what the reality is, a CEO of an investment company will always say "you can't outperform the market".  If they say otherwise they could be open to legal problems.

I don't doubt that LC has lots of smart people working for them, but they are optimizing for something different than investors.  On page 9, he says "interest rates is really a way for us to manage supply and demand."

All of their smart people are spending time making sure that supply and demand are equalized and loans are being originated.  They are not necessarily optimizing for the best interest rate based upon actual risk.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: cfb on July 22, 2014, 09:13:45 PM
The problem with data driven note selection becomes evident when you look at this problem from the other end of the funnel.  The reasons why loans default.

 - Scammer with a history of funny business in their credit report that becomes evident with analysis.  I have to say I've found a few of these and wondered how they got through the LC screening.  You can certainly weed out some percentage of loans but I wish LC would not pass through a "B" loan with a 600-something fico and a lot of derogatories.
 - Someone with a perfectly good credit rating that fully intends to take the money and declare bankruptcy.  You can't spot this person.  I've seen 750+ clean and clear borrowers make <3 payments and then roll over
 - Someone with a perfectly good looking data set that suddenly loses their high paying job and can't get another one, develops a major illness or gets in a car accident, gets blindsided by a divorce, suffers a natural disaster, their business burns down, etc.  You cant filter these out either.
 - Someone with stuff in the downloaded data that creates a suspicion, but that data isn't exposed by the standard LC filtration system.  While you can download and analyze, generally good loans wont last long enough for you to do that.  I've seen someone taking a consolidation loan that looked awesome by the standard LC web site filter, but when looking at the data you see they have 9 mortgages out and a bunch of other stuff that shows that you're really making a small business loan to a property owner.  If I recall correctly (a dubious prospect) they also didn't show things like home equity lines of credit used and a few other things that might indicate someone teetering on the edge.

There are probably more reasons, but it seems like a good percentage of defaults look a lot more like the last three than the first one.

All of this reminds me of stock market analysis.  You can surely weed out the real losers but sometimes there are some pretty loser-looking companies or sectors that are really more than fairly priced and with patience will come back.  Anyone want to buy a lot of bank/financial stocks in 2008?  And these companies are analyzed and regulated out the wazoo compared to someone who wants to try an untraditional p2p loan.  I suspect the reason why the market exists is because LC is somewhat immune to defaults and the banks know they need to charge more to account for the stuff they just won't see coming.

It happens in equities too.  You find out the execs are fiddling the numbers, committing crimes or fraud of some kind, products that don't really exist, customers that don't really exist, etc.

I think the basic functional rationale for equity investing applies to p2p as well.  Those that concentrate their investments and basically get lucky get rich.  Those that aren't lucky lose their shirts.  Those that diversify broadly or use indexes tend to do better than most when looking at longer periods of time and the longer the time period the more average things become.  Experts that 'beat the market' hit the wall.

Then you have the various biases that help people remember their successes and forget their losses.  And I'm also willing to bet that most folks that don't do well with this end up on a forum telling someone about it, but if they're getting better than average they're probably looking for an outlet to declare their success.  And I've seen more than a few people who say they're doing better at investing than they really are.

So if a majority of this is human stuff and unpredictable occurrences, then the best you're likely to do long term is improve your situation by a little bit by avoiding real obvious losers.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: JoeB on July 22, 2014, 10:49:32 PM
- Someone with stuff in the downloaded data that creates a suspicion, but that data isn't exposed by the standard LC filtration system.  While you can download and analyze, generally good loans wont last long enough for you to do that.  I've seen someone taking a consolidation loan that looked awesome by the standard LC web site filter, but when looking at the data you see they have 9 mortgages out and a bunch of other stuff that shows that you're really making a small business loan to a property owner.  If I recall correctly (a dubious prospect) they also didn't show things like home equity lines of credit used and a few other things that might indicate someone teetering on the edge.

No truer words were ever spoken.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: rawraw on July 23, 2014, 07:51:55 AM

So if a majority of this is human stuff and unpredictable occurrences, then the best you're likely to do long term is improve your situation by a little bit by avoiding real obvious losers.
We don't get to price the risk, since we aren't underwriting.  The only thing we can do is find loans that are mispriced, in the sense that they have a C1 yield but a B2 probability of default.  Which is ultimately what you are saying
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: hoggy1 on July 23, 2014, 09:56:13 AM
This is quite an important thread and I am glad RobL not only asked the question but revived the discussion or I might never have seen it.

My scoring model does not use FICO or loan grade but does have an interest rate minimum (ie I am pursuing a high risk strategy). I am always astonished that there never seems to be any correlation between my score and  LC's loan grade or FICO! My account is young so the only indication I have that I am doing anything correctly is that in order to purchase loans that score over 900 in my model I have to purchase within the first minute after release and even then I often am locked out as they are fully funded. Maybe I'm just another lemming.

I have kept my account small while I dabble and get the feel of this marketplace precisely because I can't answer Rob's question.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: AnilG on July 23, 2014, 10:23:19 AM
Why don't you use FICO in your scoring model?

This is quite an important thread and I am glad RobL not only asked the question but revived the discussion or I might never have seen it.

My scoring model does not use FICO or loan grade but does have an interest rate minimum (ie I am pursuing a high risk strategy). I am always astonished that there never seems to be any correlation between my score and  LC's loan grade or FICO! My account is young so the only indication I have that I am doing anything correctly is that in order to purchase loans that score over 900 in my model I have to purchase within the first minute after release and even then I often am locked out as they are fully funded. Maybe I'm just another lemming.

I have kept my account small while I dabble and get the feel of this marketplace precisely because I can't answer Rob's question.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: turing on July 23, 2014, 12:06:02 PM
Those that diversify broadly or use indexes tend to do better than most when looking at longer periods of time and the longer the time period the more average things become.  Experts that 'beat the market' hit the wall.

Diversification is still very important for any investor using a model.  Like you said, there are many reasons people will default.  People are unpredictable on the individual level, but taken in a large group they can be predicted.  I won't do very well predicting which number will show up on a dice in 1 roll, but I can do a very good job telling you the number of times a number will show up on 1,000 rolls.

Why don't you use FICO in your scoring model?

In my opinion, FICO and Lending Club's rating are important data points for other models to use.

With the Netflix competition to improve their movie rating predictions the top teams were those that combined models with other teams.  During the competition, teams that weren't winning would combine models and jump ahead of other teams.  Those other teams would combine models and jump ahead again.
http://www.wired.com/2009/09/how-the-netflix-prize-was-won/

FICO and Lending Club subgrade are risk models that use different inputs.  Making another risk model that combines those and adds other factors is effectively doing what the winners of the Netflix prize did.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: hoggy1 on July 23, 2014, 12:14:49 PM
I overstated a little. I do have FICO in the model as a secondary factor, ie larger FICOs do push up the score but notes can get scores over 900 with a FICO of 660. If I have cash I purchase every loan that scores over 900 and unless it is a California note I generally have to make that purchase within 60 seconds of release. In the last 3 months I have only seen one note that scored 900 that wasn't from CA and still appeared in a csv not downloaded within the first minute after release time.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: trevor on July 23, 2014, 03:54:22 PM
How can people deny that some notes are simply better than others? P2P lending CAN be accurately predicted, unlike the stock market. Banks do it all the time for their loans. Sure, some notes will randomly default and you can't do anything about that, but you certainly can raise your returns to be above-average. 


Riddle me this: If all loans are created equal, why is there a 2.69% ROI difference between refinancing loans and all other loan types? This includes EVERY loan issued.


https://www.nickelsteamroller.com/#!/stats/lendingclub


How can you honestly say that refinancing loans AREN'T better than other loan types? This is just an example, there's plenty of filters out there that will beat the average.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: trevor on July 23, 2014, 04:25:32 PM
Here's another one. This includes every note issued, sorted by annual income and ROI. Note that every group is around the same average rate and the same average age. Yet the high income loans tend to have much better ROI. Is there any denying that investing in high income notes will most likely lead to higher returns?


(https://forum.lendacademy.com/proxy.php?request=http%3A%2F%2Fi.imgur.com%2FUoZWJEu.png&hash=e3ee7b93f26992e3673b6a288f9520a9)
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Rob L on July 23, 2014, 05:08:22 PM
So, I thought let's see how debt financing did last year.
I was too lazy to post a screen shot, but anyway:
All loans made by LC 1/1/2013 - 12/31/2013 sorted highest to lowest ROI (courtesy of NSR):

Purpose                        ROI       # of  Loans
------------------------ ---------     ------------
 renewable_energy       17.35%          51       
 vacation                     12.27%        565       
 other                         11.95%      5,839         
 wedding                     11.66%         595       
 medical                      11.15%         888   
 moving                      11.07%         639
 debt_consolidation      10.65%    80,609     
 house                        10.50%         675       
 credit_card                 10.43%    32,790
 small_business             9.66%      1,357
 home_improvement      9.61%      7,400
 car                              7.75%      1,050   
 major_purchase           7.48%      2,298

It isn't clear to me that LC hasn't updated its model over the past 7 years to more accurately price all the various loan purposes.
That's kinda my point.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: trevor on July 23, 2014, 05:41:00 PM
I see what you're getting at, but that's much too small of a sample size. Here's data from the beginning of 2012 onwards:


(https://forum.lendacademy.com/proxy.php?request=http%3A%2F%2Fi.imgur.com%2FrK94Fep.png&hash=af3ffa7d1b41b324b33f7be1210e758c)
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: hoggy1 on July 23, 2014, 05:48:47 PM
Purpose                     ROI      Count                            
credit_card                  9.95%    43,154                           
debt_consolidation      9.59%   111,424                           
home_improvement     8.78%   10,293                           
other                            8.56%    8,892                           
wedding                       8.33%   1,330                           
medical                        7.88%   1,519                           
vacation                       7.36%   909                           
car                               7.14%   1,951                           
house                          7.01%   1,093                           
major_purchase          6.60%   3,655                           
moving                        6.39%   1,038                           
small_business           3.65%   2,743                           
renewable_energy     3.52%   122               

Yes, but here is the same list from NS with loans beginning one year earlier    (1/1/2012 instead of 1/1/2013). Completely upside down picture with renewable_energy dead last. (small count on these loans in both cases)

I'll share an added reason I favor CC and debt consolidation loans. If the borrowers actually use the loans for the stated purpose then in general their FICO scores should go up as they trade revolving credit for installment credit and I can monitor whether that happens.   
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: hoggy1 on July 23, 2014, 05:50:56 PM
You beat me to it trevor!
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: trevor on July 23, 2014, 05:57:50 PM


I'll share an added reason I favor CC and debt consolidation loans. If the borrowers actually use the loans for the stated purpose then in general their FICO scores should go up as they trade revolving credit for installment credit and I can monitor whether that happens.


Agreed, although I don't really monitor individual notes. When someone takes out a loan for refinancing they are actually IMPROVING their financial situation. Any other type of loan is simply adding more debt, leading to higher default rates. I don't see any reasons to believe otherwise.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: rawraw on July 23, 2014, 06:17:03 PM


I'll share an added reason I favor CC and debt consolidation loans. If the borrowers actually use the loans for the stated purpose then in general their FICO scores should go up as they trade revolving credit for installment credit and I can monitor whether that happens.


Agreed, although I don't really monitor individual notes. When someone takes out a loan for refinancing they are actually IMPROVING their financial situation. Any other type of loan is simply adding more debt, leading to higher default rates. I don't see any reasons to believe otherwise.
Sounds like a good story, but the data could go either way.  You really have to know more.  You'd rather invest in a 660 FICO refinance note than a 800 FICO addition to house note?  This is why you can't view variables in isolation, variables influence each others important in the formula.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: trevor on July 23, 2014, 06:37:56 PM


I'll share an added reason I favor CC and debt consolidation loans. If the borrowers actually use the loans for the stated purpose then in general their FICO scores should go up as they trade revolving credit for installment credit and I can monitor whether that happens.


Agreed, although I don't really monitor individual notes. When someone takes out a loan for refinancing they are actually IMPROVING their financial situation. Any other type of loan is simply adding more debt, leading to higher default rates. I don't see any reasons to believe otherwise.
Sounds like a good story, but the data could go either way.  You really have to know more.  You'd rather invest in a 660 FICO refinance note than a 800 FICO addition to house note?  This is why you can't view variables in isolation, variables influence each others important in the formula.


You bring up some good points, but you fail to remember one important thing: We can use more than one single filter for our loans, and that is how you can beat the average.

Did you see the years of data I posted on the last page? Or was all of that a fluke? You could even blindly invest in debt/credit refinancing and you would get above average returns, because some loan types are simply better than others.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: rawraw on July 24, 2014, 06:55:47 AM


I'll share an added reason I favor CC and debt consolidation loans. If the borrowers actually use the loans for the stated purpose then in general their FICO scores should go up as they trade revolving credit for installment credit and I can monitor whether that happens.


Agreed, although I don't really monitor individual notes. When someone takes out a loan for refinancing they are actually IMPROVING their financial situation. Any other type of loan is simply adding more debt, leading to higher default rates. I don't see any reasons to believe otherwise.
Sounds like a good story, but the data could go either way.  You really have to know more.  You'd rather invest in a 660 FICO refinance note than a 800 FICO addition to house note?  This is why you can't view variables in isolation, variables influence each others important in the formula.


You bring up some good points, but you fail to remember one important thing: We can use more than one single filter for our loans, and that is how you can beat the average.

Did you see the years of data I posted on the last page? Or was all of that a fluke? You could even blindly invest in debt/credit refinancing and you would get above average returns, because some loan types are simply better than others.
Trevor, I don't mean to insult you but what background do you have in data analysis and/or consumer debt?  Because you seem to cling to those numbers like a safety blanket.  I think I've previously talked to you about data mining in another thread, but you don't seem willing to listen.

And your comment doesn't solve the problem.  Filters are binary (match/disallowed).  That's not how the variables interact with each other as sometimes a criteria should not be disallowed based on other criteria existing.  Assuming FICO perfectly rank orders risk (which it wouldn't in this case, but ignore that), you'd want to assign a better grade to 800 buy a car than a  660 refinance my car.  If you filtered only refinance a car, you'd eliminate the 800 purchase.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: hoggy1 on July 24, 2014, 10:40:08 AM
And your comment doesn't solve the problem.  Filters are binary (match/disallowed).  That's not how the variables interact with each other as sometimes a criteria should not be disallowed based on other criteria existing.  Assuming FICO perfectly rank orders risk (which it wouldn't in this case, but ignore that), you'd want to assign a better grade to 800 buy a car than a  660 refinance my car.  If you filtered only refinance a car, you'd eliminate the 800 purchase.

I agree rawraw,
My model uses lots of interactions between parameters and is the primary reason I do not use any of the third-party automated platforms. None, that I know of (Please correct me) permit me to filter on relationship within the data. Here is the simplest possible example: I want the borrowers installment payment to be less than 10% of monthly income AND their DTI < 25% so that I am sure their DTI including this loan will be less than 35%. Although this PTI (payment to income) has been mentioned elsewhere (not my invention) I have not seen any 3rdparty sites that allow me to specify such relationships. I need to be able to specify formulas much like in excel.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: cfb on July 24, 2014, 12:06:37 PM
20,000 researchers examined thousands of terabytes of data gathered since January of 2009.  In every analysis Obama was president, he was alive, and the stock market went up on an annualized basis.

Researchers concluded that based on the long trend of evidence, Obama would always be president, he would live forever, and as long as he was president the stock market would always go up.  An alternate theory was developed that the rising stock market caused Obama to be president, and also gave him immortality.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: rawraw on July 24, 2014, 05:27:18 PM
Oh, you are good CFB. 
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Fred93 on July 24, 2014, 06:54:06 PM
Thank you CFB.
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: Randawl on July 24, 2014, 10:34:22 PM
I was in the process of typing something similar.  Changed my mind and saw hours later that rawraw and cfb said it better anyway.     ;)
Title: Re: What's This "Best Note" Selection Business Anyway?
Post by: cfb on July 25, 2014, 03:55:41 PM
Its an old one I just updated a little.

The other comment that falls to mind during moments of intense data and trend analysis is what Isaac Newton said after losing his shirt in the South Sea bubble.  "I can calculate the movement of the stars, but not the madness of men".