Enhancing investment decisions in P2P lending: an investor composition perspective

P2P lending, as a novel economic lending model, has imposed new challenges about how to make effective investment decisions. Indeed, a key challenge along this line is how to align the right information with the right people. For a long time, people have made tremendous efforts in establishing credit records for the borrowers. However, information from investors is still under-explored for improving investment decisions in P2P lending. To that end, we propose a data driven investment decision-making framework, which exploits the investor composition of each investment for enhancing decisions making in P2P lending. Specifically, we first build investor profiles based on quantitative analysis of past performances, risk preferences, and investment experiences of investors. Then, based on investor profiles, we develop an investor composition analysis model, which can be used to select valuable investments and improve the investment decisions. To validate the proposed model, we perform extensive experiments on the real-world data from the world's largest P2P lending marketplace. Experimental results reveal that investor composition can help us evaluate the profit potential of an investment and the decision model based on investor composition can help investors make better investment decisions.

[1]  Dave Feldman,et al.  Mortgage Default: Classification Trees Analysis , 2004 .

[2]  Samprit Chatterjee,et al.  A Nonparametric Approach to Credit Screening , 1970 .

[3]  Kin Keung Lai,et al.  A new fuzzy support vector machine to evaluate credit risk , 2005, IEEE Transactions on Fuzzy Systems.

[4]  O. Mangasarian.  Linear and Nonlinear Separation of Patterns by Linear Programming , 1965 .

[5]  Rashmi Malhotra,et al.  Differentiating between Good Credits and Bad Credits Using Neuro-Fuzzy Systems , 2001, Eur. J. Oper. Res..

[6]  Li Xiao,et al.  Building a Scalable Bipartite P2P Overlay Network , 2007, IEEE Trans. Parallel Distributed Syst..

[7]  Halina Frydman,et al.  Testing the Adequacy of Markov Chain and Mover-Stayer Models as Representations of Credit Behavior , 1985, Oper. Res..

[8]  Maria Stepanova,et al.  Survival Analysis Methods for Personal Loan Data , 2002, Oper. Res..

[9]  Petter Holme,et al.  Network bipartivity. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[10]  Yoshi Fujiwara,et al.  Complex networks and economics , 2003 .

[11]  George M. Constantinides,et al.  Handbook of the Economics of Finance , 2013 .

[12]  Hui Wang,et al.  People-to-People Lending: The Emerging e-Commerce Transformation of a Financial Market , 2009, AMCIS.

[13]  James S. Linck,et al.  The Determinants of Board Structure , 2007 .

[14]  S. C. Berger,et al.  Emergence of Financial Intermediaries in Electronic Markets: The Case of Online P2P Lending , 2009 .

[15]  R. Thaler,et al.  A Survey of Behavioral Finance , 2002 .

[16]  Sergio Herrero-Lopez,et al.  Do Lenders Make Optimal Decisions in a Peer-to-Peer Network? , 2009, 2009 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology.

[17]  Merton H. Miller.  The Cost of Capital, Corporation Finance and the Theory of Investment , 1958 .

[18]  Herbert L. Jensen,et al.  Using Neural Networks for Credit Scoring , 1992 .

[19]  L. Thomas.  Consumer credit models: pricing, profit and portfolios , 2009 .

[20]  Jonathan Crook,et al.  Credit Scoring Models in the Credit Union Environment Using Neural Networks and Genetic Algorithms , 1997 .

[21]  Ari Natter,et al.  To fund or not to fund , 2008 .

[22]  R. Krishnan,et al.  A Search Theoretic Model of Person-to-Person Lending , 2008 .

[23]  S. Uryasev,et al.  Credit cards scoring with quadratic utility functions , 2002 .

[24]  Robert Hampshire,et al.  Sending mixed signals: multilevel reputation effects in peer-to-peer lending markets , 2010, CSCW '10.

[25]  Kin Keung Lai,et al.  Credit scorecard based on logistic regression with random coefficients , 2010, ICCS.

[26]  Tian-Shyug Lee,et al.  A two-stage hybrid credit scoring model using artificial neural networks and multivariate adaptive regression splines , 2005, Expert Syst. Appl..

[27]  A. Stuart,et al.  Portfolio Selection: Efficient Diversification of Investments , 1959 .

[28]  Eric Rosenberg,et al.  Quantitative Methods in Credit Management: A Survey , 1994, Oper. Res..

[29]  G. Jin,et al.  Do Social Networks Solve Information Problems for Peer-to-Peer Lending? Evidence from Prosper.Com , 2008 .

[30]  Jih-Jeng Huang,et al.  Two-stage genetic programming (2SGP) for the credit scoring model , 2006, Appl. Math. Comput..

[31]  Vikas Jain.  From Efficient Markets Theory to Behavioral Finance , 2003 .

[32]  J. Wiginton.  A Note on the Comparison of Logit and Discriminant Models of Consumer Credit Behavior , 1980, Journal of Financial and Quantitative Analysis.

[33]  G. Jin,et al.  Do Social Networks Solve Information Problems for Peer-to-Peer Lending? Evidence from Prosper.Com , 2008 .

[34]  Lean Yu,et al.  Bio-Inspired Credit Risk Analysis: Computational Intelligence with Support Vector Machines , 2008 .

[35]  M. Rubinstein..  Markowitz's "Portfolio Selection": A Fifty-Year Retrospective , 2002 .

[36]  Jyrki Wallenius,et al.  Borrower Decision Aid for people-to-people lending , 2010, Decis. Support Syst..