Borrower-lender Information Fusion for P2P Lending: A Nonparametric Approach

Received: 25 March 2018 Accepted: 16 May 2019 As known to us, tremendous efforts have been made to exploit information from borrower's credit for loan evaluation in P2P lending, but seldom researches have explored information from investors and borrowers. To this end, we propose an integrated loan evaluation model that exploits and fuses multi-source information from both the borrower and the investor for improving investment decisions in P2P lending. First, based on the borrower's credit, we build a kernel-based credit risk model to quantitatively evaluate each loan. Second, we build an investor composition model that exploits information from the investor's investment behavior for loan evaluation. Then, based on the above two quantitative models and correlation, we define a multi-kernel weight and develop an integrated loan assessment model that can evaluate a loan with both the return and risk. Furthermore, based on the integrated information loan evaluation model, we formalize the investment decisions in P2P lending as a portfolio optimization problem with boundary constraints to help investor make better investment decisions. To validate the proposed model, we perform extensive experiments on the realworld data from the world's largest P2P lending marketplace. Experimental results reveal that the integrated loan evaluation model can significantly enhance investment performance beyond the existing model in P2P market and other baseline models.

[1]  Andreas Mild,et al.  How low can you go? — Overcoming the inability of lenders to set proper interest rates on unsecured peer-to-peer lending markets , 2015 .

[2]  Jason Weston,et al.  Gene functional classification from heterogeneous data , 2001, RECOMB.

[3]  Gaurav Thakur,et al.  Deterministic Bayesian Information Fusion and the Analysis of its Performance , 2013, 1311.3755.

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

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

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

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

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

[9]  S. Viswanathan,et al.  Home Bias in Online Investments: An Empirical Study of an Online Crowdfunding Market , 2014 .

[10]  Jian Luo,et al.  A new approach for reject inference in credit scoring using kernel-free fuzzy quadratic surface support vector machines , 2018, Appl. Soft Comput..

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

[12]  Allen N. Berger,et al.  Bank size, lending technologies, and small business finance , 2011 .

[13]  Devin G. Pope,et al.  What’s in a Picture? , 2011, The Journal of Human Resources.

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

[15]  A. Srividya,et al.  Multi-Sensor Data Fusion in Cluster based Wireless Sensor Networks Using Fuzzy Logic Method , 2008, 2008 IEEE Region 10 and the Third international Conference on Industrial and Information Systems.

[16]  Bernhard Schölkopf,et al.  Support Vector Machine Applications in Computational Biology , 2004 .

[17]  Francisco Herrera,et al.  A position and perspective analysis of hesitant fuzzy sets on information fusion in decision making. Towards high quality progress , 2016, Inf. Fusion.

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

[19]  Jyrki Wallenius,et al.  Bidding strategies for real-life small loan auctions , 2011, Decis. Support Syst..

[20]  Daniel J. Brass,et al.  Friendships in Online Peer-to-Peer Lending: Pipes, Prisms, and Relational Herding , 2015, MIS Q..

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

[22]  Shuai Zhang,et al.  A novel multi-stage hybrid model with enhanced multi-population niche genetic algorithm: An application in credit scoring , 2019, Expert Syst. Appl..

[23]  Weihua Xu,et al.  A novel approach to information fusion in multi-source datasets: A granular computing viewpoint , 2017, Inf. Sci..

[24]  Hui Xiong,et al.  Instance-based credit risk assessment for investment decisions in P2P lending , 2016, Eur. J. Oper. Res..

[25]  Lionel Valet,et al.  A statistical overview of recent literature in information fusion , 2001 .

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

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

[28]  Yun Xu,et al.  A Decision Support System for Borrower's Loan in P2P Lending , 2011, J. Comput..

[29]  David M. Markowitz,et al.  Peer to Peer Lending: The Relationship Between Language Features, Trustworthiness, and Persuasion Success , 2011 .

[30]  Shawndra Hill,et al.  Expert Stock Picker: The Wisdom of (Experts in) Crowds , 2011, Int. J. Electron. Commer..

[31]  E. Nadaraya On Non-Parametric Estimates of Density Functions and Regression Curves , 1965 .

[32]  Jing Qiu,et al.  Dynamic weighted ensemble classification for credit scoring using Markov Chain , 2018, Applied Intelligence.

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

[34]  E. Nadaraya On Estimating Regression , 1964 .

[35]  Carlos Serrano-Cinca,et al.  Determinants of Default in P2P Lending , 2015, PloS one.

[36]  Carlos Serrano-Cinca,et al.  The use of profit scoring as an alternative to credit scoring systems in peer-to-peer (P2P) lending , 2016, Decis. Support Syst..

[37]  Lance A. Young,et al.  Trust and Credit: The Role of Appearance in Peer-to-peer Lending , 2012 .

[38]  Junping Du,et al.  A Sequential Approach to Market State Modeling and Analysis in Online P2P Lending , 2018, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[39]  Mingfeng Lin,et al.  Market Mechanisms in Online Peer-to-Peer Lending , 2017, Manag. Sci..

[40]  Hui Xiong,et al.  Enhancing investment decisions in P2P lending: an investor composition perspective , 2011, KDD.

[41]  Xiaohong Yuan,et al.  Engine fault diagnosis based on multi-sensor information fusion using Dempster-Shafer evidence theory , 2007, Inf. Fusion.

[42]  Vural Aksakalli,et al.  Risk assessment in social lending via random forests , 2015, Expert Syst. Appl..

[43]  Ester Faia,et al.  P2P Lending: Information Externalities, Social Networks and Loans' Substitution , 2017 .

[44]  U. Dholakia,et al.  Tell Me a Good Story and I May Lend you Money: The Role of Narratives in Peer-to-Peer Lending Decisions , 2011 .

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

[46]  Richard Taylor Interpretation of the Correlation Coefficient: A Basic Review , 1990 .

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

[48]  Enrichetta Ravina Love & Loans: The Effect of Beauty and Personal Characteristics in Credit Markets , 2012 .

[49]  Nikos Alexandris,et al.  A New Paradigm for Secure Social Lending , 2009, e-Democracy.

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

[51]  Rick L. Andrews,et al.  Strategic Herding Behavior in Peer-to-Peer Loan Auctions , 2010 .

[52]  Yuliya Komarova Loureiro,et al.  When can a photo increase credit? The impact of lender and borrower profiles on online peer-to-peer loans , 2014 .

[53]  Jiye Liang,et al.  An information fusion approach by combining multigranulation rough sets and evidence theory , 2015, Inf. Sci..

[54]  Ethem Alpaydin,et al.  Multiple Kernel Learning Algorithms , 2011, J. Mach. Learn. Res..

[55]  Sven F. Crone,et al.  Instance sampling in credit scoring: An empirical study of sample size and balancing , 2012 .

[56]  Padraig Cunningham,et al.  A temporal network analysis reveals the unprofitability of arbitrage in The Prosper Marketplace , 2013, Expert Syst. Appl..

[57]  Yufei Xia,et al.  A boosted decision tree approach using Bayesian hyper-parameter optimization for credit scoring , 2017, Expert Syst. Appl..

[58]  Siva Viswanathan,et al.  Judging Borrowers by the Company They Keep: Friendship Networks and Information Asymmetry in Online Peer-to-Peer Lending , 2011, Manag. Sci..

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

[60]  Nello Cristianini,et al.  Kernel-Based Data Fusion and Its Application to Protein Function Prediction in Yeast , 2003, Pacific Symposium on Biocomputing.

[61]  Dan Simon,et al.  Multirate multisensor data fusion for linear systems using Kalman filters and a neural network , 2014 .

[62]  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..

[63]  Oren Rigbi,et al.  The Effects of Usury Laws: Evidence from the Online Loan Market , 2012, Review of Economics and Statistics.

[64]  Juanjuan Chen,et al.  EDUCATION PREMIUM IN THE ONLINE PEER-TO-PEER LENDING MARKETPLACE: EVIDENCE FROM THE BIG DATA IN CHINA , 2017 .

[65]  Gregor Dorfleitner,et al.  Description-text related soft information in peer-to-peer lending – Evidence from two leading European platforms , 2016 .

[66]  Lucien Wald,et al.  A European proposal for terms of reference in data fusion , 1998 .