Peer To Peer Lending Analysis Conclusions
Peer To Peer Lending Analysis Conclusions
Peer To Peer Lending Analysis Conclusions
peer-to-peer lending
Quantitative Analysis Review
Pattern Recognition
MIT Media Lab Class
Copyright 2009
OVERVIEW
• Predictive Accuracy
• Predictable with 80% accuracy Loan conversion and defaults
• Able to detect borrowers financial health by payment record
• Social Factors
• Increase odds of getting a loan when financial features are similar
• Evidence of preferential attachment with threshold number of bids
2
OVERVIEW
Business Implications
Recommendations
5
INTRODUCTION
• Ernesto Martinez-
Villalpando
6
INTRODUCTION
Outline of Analysis
• Research Inquiry
• Review of prior P2P analysis using descriptive statistics
• Analytical results: classification, feature selection,
neural networks
• Suggested tools / applications for borrowers, lenders,
P2P vendor
• Conclusions
7
RESEARCH INQUIRY Analysis of P2P Lending Activity
• P2P Vendor:
• increase loan conversion,
• create tools to help borrowers and lenders
• identify loans before default
9
P2P RESEARCH Analysis of P2P Lending Activity
Descriptive Statistics
• Data from past 3 years: 340K listings, 29K loans
• Distribution of credit scores, loan status
10
P2P RESEARCH Analysis of P2P Lending Activity
Descriptive Statistics
• Geographical distribution of members
Darker green indicates
more
members
11
P2P RESEARCH Analysis of P2P Lending Activity
12
ANALYTICAL RESULTS Analysis of P2P Lending Activity
13
ANALYTICAL RESULTS Analysis of P2P Lending Activity
Loan conversion/default
predicted ~80% accuracy
• Predict loan conversion, default with ~80% accuracy (neural net not shown)
14
ANALYTICAL RESULTS Analysis of P2P Lending Activity
Top 8 features:
- Amount Delinquent
- Open Credit Lines
- Amount Requested
- Borrower’s Max Rate
- Credit Grade
- Debt to Income Ratio
- Funding Option
- Endorsement
15
ANALYTICAL RESULTS Analysis of P2P Lending Activity
16
Analysis of P2P Lending Activity
Decision
TOOLS Tree Analysis
help borrowers get loans (increase loan
conversion)
17
TOOLS Analysis of P2P Lending Activity
18
TOOLS Analysis of P2P Lending Activity
19
Analysis of P2P Social Impact
20
FEATURE SELECTION Analysis of P2P Social Impact
21
FEATURE SELECTION Analysis of P2P Social Impact
3 bidding forces involving “social
• Most important features
interaction” behavior
• Credit Grade • Bids from First Friends
• Bids from Second Friends
• 3 Bidding Forces
• Bids from Group Members
22
Analysis of P2P Social Impact
23
Analysis of P2P Social Impact
24
Analysis of P2P Lending Activity
Recommendation:
Create useful tools for borrowers and lenders to help foster P2P
activity.
These tools should be based on decision tree and HMM models.
Development of risk models should be explored using these
techniques.
25
Analysis of P2P Social Impact
Recommendation:
26
P2P RESEARCH Analysis of P2P Lending Activity
loan or no loan?
default or pay?
Analysis Method
Introduction
feature separation graphical
Descriptive
selection methods models
statistics
Suggested
Neural decision TOOLS
greedy
Nets trees for
Peer to Peer
Linear
Lending
floating Discriminant
Analysis bayesian
networks
Principal Support
Component Vector
Analysis Machine
Hidden
experimental Markov Model
mechanical
methods loan performance
turk
group
performance
27
Analysis of P2P Social Impact
28
References for Further Study
• MIT Pattern Recognition Course Information:
• http://courses.media.mit.edu/2008fall/mas622j/
• Prior Research
• Prosper.com for information on p2p lending
• Stanford Business School regression analysis of prosper.com data
• http://www.prosper.com/Downloads/Research/Prosper_Regression_Project-Fundability_Study.pdf
• Stanford Podcast by Chris Larsen CEO of Prosper.com
http://ecdev.stanford.edu/authorMaterialInfo.html?mid=1576
• Books:
• The Complete Guide To Prosper.com by Sean Bauer
• Happy About People-to-People Lending With Prosper.com by Roger Steciak
• Competitor list:
• VirginMoneyUS.com, Zopa.com, LendingClub.com, Loanio.com, Circlelending.com, FundMyNotes.com
29