Author Topic: New note selection model & website. Would love feedback  (Read 38586 times)

rawraw

  • Hero Member
  • *****
  • Posts: 2793
    • View Profile
Re: New note selection model & website. Would love feedback
« Reply #15 on: October 27, 2014, 02:45:09 PM »
It's okay, I'm typing from a cell phone so my responses may seem curt. What's your value proposition?

turing

  • Full Member
  • ***
  • Posts: 222
    • View Profile
    • PeerToPeerQuant.com
    • Email
Re: New note selection model & website. Would love feedback
« Reply #16 on: October 27, 2014, 03:25:57 PM »
It's okay, I'm typing from a cell phone so my responses may seem curt. What's your value proposition?

Value proposition:  Pay us a small fee and increase your lending club return.

Obviously, people who already have a great lending club return won't get as much value out of it.  Our fee works out to less than 0.6% of the note (depending on how much you invest per note) so we think we can add quite a bit more value than that fee in the form of a better return.

It also doesn't take as much time or expertise as creating your own investment model.

rawraw

  • Hero Member
  • *****
  • Posts: 2793
    • View Profile
Re: New note selection model & website. Would love feedback
« Reply #17 on: October 27, 2014, 03:54:58 PM »
I guess what I'm getting at is do you think you improved on what's out there already? Or just introducing price competition

turing

  • Full Member
  • ***
  • Posts: 222
    • View Profile
    • PeerToPeerQuant.com
    • Email
Re: New note selection model & website. Would love feedback
« Reply #18 on: October 27, 2014, 05:19:10 PM »
I get your question now.  I think we do offer some benefits vs other models.

The biggest benefit is our model is not speed dependent.  There are lots of notes that fit the qualifications at all times of day.  People don't need to worry so much about API's and 3rd party services to make sure they get loans within first 5 minutes of being listed.

The other models out there are not inherently speed dependent but they have become a victim of their own success because so many people/institutions use them.  It makes it harder and harder to win the race to buy their recommendations.


rawraw

  • Hero Member
  • *****
  • Posts: 2793
    • View Profile
Re: New note selection model & website. Would love feedback
« Reply #19 on: October 27, 2014, 07:07:44 PM »
Do you have the option to sort by probability of default?  That's what I'm really looking for in a model.  I could care less about the expected returns of the models that use only one part of a credit cycle but I am interested in calculating the probability of default and determining which loans I'd like to invest.  I'm not trying to maximize income for tomorrow.  I'm trying to hit a certain return benchmark with notes that I think won't be as volatile.

Fred

  • Hero Member
  • *****
  • Posts: 1421
    • View Profile
Re: New note selection model & website. Would love feedback
« Reply #20 on: October 27, 2014, 10:26:02 PM »
The biggest benefit is our model is not speed dependent. 

"Not speed dependent" is your biggest benefit? ;-)

The other models out there are not inherently speed dependent but they have become a victim of their own success because so many people/institutions use them.  It makes it harder and harder to win the race to buy their recommendations.

Have you tested that your model produces sufficiently different results than those of other models?

Furthermore, how do you ensure that the above situation -- a victim of own success -- does not apply to you when many people use your model?

lascott

  • Hero Member
  • *****
  • Posts: 1435
    • View Profile
    • Appreciate my post and want to try LendingRobot? URL below
Re: New note selection model & website. Would love feedback
« Reply #21 on: October 28, 2014, 01:38:50 AM »
Does the option of picking a particular note disappear once you've selected it once?
i.e. if I picked that 13.98% 36 month note mid-morning and went looking for more notes mid-afternoon would it still be there if it is was not 100% funded?  That is could I mistake it for a new note and pick it a 2nd (unwanted) time?


Tools I use: (main) BlueVestment: https://www.bluevestment.com/app/pricing + https://www.interestradar.com/ , (others) Lending Robot referral link: https://www.lendingrobot.com/ref/scott473/  & Peercube referral code: DFVA9Y

turing

  • Full Member
  • ***
  • Posts: 222
    • View Profile
    • PeerToPeerQuant.com
    • Email
Re: New note selection model & website. Would love feedback
« Reply #22 on: October 28, 2014, 11:39:09 AM »
Do you have the option to sort by probability of default?  That's what I'm really looking for in a model.  I could care less about the expected returns of the models that use only one part of a credit cycle but I am interested in calculating the probability of default and determining which loans I'd like to invest.  I'm not trying to maximize income for tomorrow.  I'm trying to hit a certain return benchmark with notes that I think won't be as volatile.

We do not have an ability to sort by default probability.  Sorry.  With the nature of the genetic algorithm, it doesn't really calculate a default risk per note.  It creates a set, or multiple sets of criteria, that have a good expected return.


"Not speed dependent" is your biggest benefit? ;-)

Besides the good return :)
rawraw wanted to know what made it different than other models which also have a good return.

Have you tested that your model produces sufficiently different results than those of other models?

No we have not done an actual study to see which notes we select vs other models.  This would be an intersting thing to compare at some point.

Many people say they have a hard time finding notes that meet the criteria of other models.  Even if they act right at release time.

Our model has lots of notes available throughout the day so a large portion of our notes must be different than other models.

Furthermore, how do you ensure that the above situation -- a victim of own success -- does not apply to you when many people use your model?

Good question.  That is a great problem to have (for us) but there is no easy way around it if there are lots of users.  It isn't an immediate concern at this point so we haven't spent any time thinking of a solution.  If it does become a problem we will look into possible solutions.

turing

  • Full Member
  • ***
  • Posts: 222
    • View Profile
    • PeerToPeerQuant.com
    • Email
Re: New note selection model & website. Would love feedback
« Reply #23 on: October 28, 2014, 11:41:35 AM »
Does the option of picking a particular note disappear once you've selected it once?
i.e. if I picked that 13.98% 36 month note mid-morning and went looking for more notes mid-afternoon would it still be there if it is was not 100% funded?  That is could I mistake it for a new note and pick it a 2nd (unwanted) time?

If you click on a loan it is not shown on the main note list next time to help people avoid duplicate purchases.  If you don't click on it, it will still be there next time as long as it isn't 100% funded.

If you click on your user name in the upper right corner you will go to your settings page and can see previous notes you clicked on.

c) I'm not sure I like the payment for note that don't get funded or completed (ie. Order complete: 1 Note(s) not issued email).  I realize it is hard to track (lendingrobot does) and it is "only" $0.15.  All in all it seems like the P2P-Picks concept was if memory serves me (but they never ended up billing).

I wanted to update you on this feature request.

For regulatory reasons we can't add this feature.  Our service now is not based upon your buy or sell of the note.  You make the final decision and the note might not even fund.  If we refunded fees if the note didn't fund, it could be viewed as being paid per purchase, which might require registration as investment advisors.

We set the fee at a point where we hoped users wouldn't mind some notes that didn't fund.  Sorry we can't implement that feature.
« Last Edit: October 28, 2014, 11:52:01 AM by turing »

rawraw

  • Hero Member
  • *****
  • Posts: 2793
    • View Profile
Re: New note selection model & website. Would love feedback
« Reply #24 on: October 30, 2014, 06:32:49 AM »
Besides using the 1 month old results, do you release what the net return would be on already seasoned notes in the historical file?  Anyone can be in the top 99th percentile in the first month.
« Last Edit: October 30, 2014, 06:38:11 AM by rawraw »

lascott

  • Hero Member
  • *****
  • Posts: 1435
    • View Profile
    • Appreciate my post and want to try LendingRobot? URL below
Re: New note selection model & website. Would love feedback
« Reply #25 on: October 30, 2014, 10:02:35 AM »
How often (when) are the notes listed updated?
Tools I use: (main) BlueVestment: https://www.bluevestment.com/app/pricing + https://www.interestradar.com/ , (others) Lending Robot referral link: https://www.lendingrobot.com/ref/scott473/  & Peercube referral code: DFVA9Y

turing

  • Full Member
  • ***
  • Posts: 222
    • View Profile
    • PeerToPeerQuant.com
    • Email
Re: New note selection model & website. Would love feedback
« Reply #26 on: October 30, 2014, 10:42:56 AM »
How often (when) are the notes listed updated?

The note list is updated every 5 minutes 24/7.  For now that produces lots of results.  If fewer notes start showing up or they are quickly purchased we will start updating quicker and take other action needed to speed up the process.

Besides using the 1 month old results, do you release what the net return would be on already seasoned notes in the historical file?  Anyone can be in the top 99th percentile in the first month.

We haven't released that info but I can get it from the programmer and release it.  I will ask him for those numbers.

I agree that with all accounts considered 3 month old accounts can be in the 99th percentile really easily.  But with similar age only that is a mathematical impossibility given the definition of percentile :)

rawraw

  • Hero Member
  • *****
  • Posts: 2793
    • View Profile
Re: New note selection model & website. Would love feedback
« Reply #27 on: October 30, 2014, 07:05:27 PM »
No it's not.  All you have to do is invest in the highest interest rate notes possible and invest in nothing else.  As long as they all don't turn out to be first payment defaults, you'd be at the very top even of liked age accounts.  But I'm curious what the long term results are, so I'll keep posted

rawraw

  • Hero Member
  • *****
  • Posts: 2793
    • View Profile
Re: New note selection model & website. Would love feedback
« Reply #28 on: October 31, 2014, 10:37:17 AM »
BTW you may want to request a subforum for your product.

turing

  • Full Member
  • ***
  • Posts: 222
    • View Profile
    • PeerToPeerQuant.com
    • Email
Re: New note selection model & website. Would love feedback
« Reply #29 on: October 31, 2014, 11:35:03 AM »
No it's not.  All you have to do is invest in the highest interest rate notes possible and invest in nothing else.  As long as they all don't turn out to be first payment defaults, you'd be at the very top even of liked age accounts.  But I'm curious what the long term results are, so I'll keep posted

I see what you are saying.  Maybe we should add a 3rd percentile then, similar age AND similar weighted average interest rate.  That data is in the JSON so it is just a matter of pulling it out and calculating it.

Thanks for following our progress.  I can definitely understand wanting more history behind it before committing to the model.

Good idea about requesting a subforum.  I hadn't thought about that but I will ask Peter.