Clicky

  • Welcome to P2P Lending / NFT Lending Forum.
 

ETH.LOAN

News:

This was the original Lend Academy peer-to-peer lending forum, since forensically restored by deBanked and now reintroduced to eth.loan.

To restore access to your user account, email [email protected]. We apologize for errors you may experience during the recovery.

Main Menu
NEW LOANS:   | 804.eth 2.500 Ξ | remoraid.eth 0.299 Ξ | remoraid.eth 0.299 Ξ | ALL

Is there other data you want to see on Note page?

Started by Peter, November 16, 2014, 11:00:00 PM

Previous topic - Next topic

turing

Right now our note page shows 3 data points (subgrade, interest rate, term, loan purpose).  Like this:
https://www.peertopeerquant.com/images/how-fit-invest-buttons.png" alt="" class="bbc_img" />

Is there other loan data you would want to see when deciding which notes to buy?

rawraw

How does the picks work?  Is there a hurdle rate for minimum return or is there a credit score associated with the pick?  Should I view all picks the same or is there some better than others?


TravelingPennies

What about maturity term ? Does that need to be random as well?

TravelingPennies

Maturity is the same.  The algorithm would have tried just 36 month or just 60 month.  Choosing only one or the other would not improve your return. 

That being said, it might not lower your expected return.

With any good filtering decision there some "cost" you consider when adding new variables.  The new variables need to increase the return enough to make it worth adding.  If you don't do this, you run the risk of over fitting the model.

I opened this thread because we want to offer what users want.  Lots of users have mentioned the ability to filter or see more info so they can choose only certain loans.  I wanted to know what info would help users make their investment decisions.

TravelingPennies

Well that's why I was curious about these things -- because if they existed, I'd want to see them ha ha

lascott

I would guess most peoples concern is that you don't have a track record and are asking people to trust your programming: "Our algorithm tried hundreds of thousands of combinations of variables and combinations of filters to give the ones that give the best return."   P2P-Picks is/was probably different as the author has a known background (podcast interview by Peter(LA), stats background, etc), has a commercial product, few years of performance history, and work with each drop.

I waited a several day to respond.  In my order of preference.
1) FICO
2) Employment years
3) Credit Utilization
4) Months since Last Delinquencies
5) Income
6) Loan Amount
7) When originated (i.e. how long ago did the loan get originated - days since first showed up on one of the 4 drops)


NEW LOANS:   | 804.eth 2.500 Ξ | remoraid.eth 0.299 Ξ | remoraid.eth 0.299 Ξ | ALL