P2P Lending Platforms Research Articles

The mechanism and effectiveness of credit scoring of P2P lending platform

PurposeThe purpose of this paper is to investigate the mechanism how the platform obtains and uses undisclosed information to determine individual borrowers’ credit score and to examine the effectiveness of credit scoring in predicting default. The motivation stems from the fact that there is little evidence about the role of P2P platform, which has been positioned as a kind of information intermediary.Design/methodology/approachUsing a sample of 5,176 unsecured P2P loans having expired before December 31, 2015 on Renrendai.com and an approach of two-stage regression, the paper first estimates the undisclosed information embedded in credit score by regressing credit score on four types of public information about a borrower’s creditworthiness. Then, the authors use a Logit regression to examine the role of the excess information in predicting the default probability.FindingsThe certification information provided by the platform is the most important determinant for a borrower’s credit score and the undisclosed information embedded in credit score can predict the loan performance better than the public information of posted listings. Moreover, the predictive ability of the undisclosed information is better for high-risk borrowers than for low-risk ones.Research limitations/implicationsProviding a credit score for each individual is a way for P2P platforms to play an information intermediary role. More evidence about whether or how a platform plays its role are worthy to be exploited by investigating a platform’s operating policies in detail and doing cross-platform comparative studies.Practical implicationsThe results about the effect of various types of information on loan performance can provide an insightful guidance for P2P platforms to optimize their mechanism on information disclosure and credit scoring.Originality/valueThe existing literature mainly focuses on the effects of information voluntarily disclosed by borrowers and the behaviors of investors on P2P lending outcomes. The paper highlights the information intermediary role played by the platform and presents empirical evidence that credit scoring for individual borrowers is a way for P2P platforms to promote the direct lending for individual.

Debt Collection on the Peer-to-peer Lending Platform Under the Situation of Chinese Culture: A Case Study of PPDai.com

In China, high default rate is always the key factor which restricts the development of the P2P lending platform In the recent years. Generally, scholars focus on the pre loan tache to reduce risk and ignore the importance of debt collection management. It’s proved that the capacity of debt collection is the key process of P2P platform for the effective control of bad debts, and then safeguard the interests of creditors. A multiple-case study of the typical P2P lending platform in China "PPDai.com" is used in our research. We found that under the circumstance of the imperfect legal system, collection through relevant contact has become the most important and the most prominent collection methods .At the same time, we discuss how relevant contacts affect the Borrower's mentality from the perspective of Chinese culture including Guanxi, shame culture and kinship culture. The conclusions of this paper give some guidance to Chinese P2P network lending collection practices, has theoretical significance and practical value.

Research on Credit Risk Assessment of P2P Network Platform: Based on the Logistic Regression Model of Evidence Weight

As an emerging credit model, P2P network credit has been developing rapidly in recent years. At the same time, it also faces many credit risk problems. This paper focuses on the credit risk of borrowers, and constructs a model of WOE and logistic regression to evaluate the risk assessment of China’s P2P network platform, Hong ling Venture. The research results show that the main factors that affect the loan success rate of P2P lending platform include loan amount, annual interest rate, bidding transaction amount and proportion of repayment on time and so on. By constructing the model of combination of the logistic regression with weight of evidence, this paper provides an appropriate method to manipulate the borrowing information of loan borrowers and evaluates the borrowing behavior of borrowers simultaneously, so that P2P credit platform can reduce the credit risk caused by borrower.

User Data Can Tell Defaulters in P2P Lending

Online peer-to-peer (P2P) lending service is a new type of financial platforms that enables individuals borrow and lend money directly from one to another. As P2P lending service is rapidly developing, a number of rating systems of borrowers’ creditworthiness are published by different P2P lending companies. However, whether these rating systems could truly reflect the creditworthiness and loan risk of borrowers is unconfirmed. In this paper, we analyzed the differences between credit levels and users’ distribution of CPLP to evaluate if the credit levels can truly reflect the borrowers’ credit. We used soft factors to establish a model that can find borrowers who are likely to default. Further, we proposed some strategies to construct and improve the risk-control of P2P lending platforms according to the result of our research.

The Financial Intermediation Role of the P2P Lending Platforms

The objective of our paper is to explore the role of P2P lending platforms through the prism of the theory of financial intermediation. P2P lending platforms perform the brokerage function of financial intermediaries by matching lenders’ supply and borrowers’ demand of funding, according to the risk and the maturity of their needs. Unlike banks, P2P lending platforms do not create money and do not perform risk and maturity transformation. However, they can organize secondary markets to trade loan contracts before maturity and some P2P lending platforms aim at providing a fixed income to lenders. To ensure efficient and sustainable financial intermediation, P2P lending platforms need to ensure that they are not subject to principal-agent problems and that their incentives coincide with those of lenders. The possibility of orderly resolution of P2P lending platforms failures might decrease moral hazard problems that are inherent in the modern financial intermediation.

Cheap Talk? The Impact of Lender-Borrower Communication on Peer-to-Peer Lending Outcomes

The limited information provided by peer-to-peer (P2P) lending platforms often is not sufficient for lenders to determine if a borrower is trustworthy and able to repay the loan. Using a unique dataset from a P2P lending platform, which allows lenders to seek information directly from borrowers and borrowers to respond to the questions and comments, we examine the impact of lender-borrower communication on funding outcomes and loan performance. Our results show that not only the amount but also the content of such direct communication matters. Specifically, the number of lender comments is negatively associated with funding success, while the number of borrower responses is positively associated with funding success, although only comments help reduce the final interest rate. The role of the communication is even stronger for listings with poor credit grades. Moreover, lenders are influenced by other lenders’ (positive or negative) comments and the quality of the information disclosed in borrower responses can affect funding outcomes. Loan performance (e.g., default ratio), however, cannot be predicted based on the amount of lender borrower communication. This research broadens and deepens our understanding of the roles of information disclosure, social influence, information quality, and trust in economic exchanges in online settings.

Evaluating the risk performance of online peer-to-peer lending platforms in China

Peer-to-peer (P2P) lending, which has received considerable research attention in recent years, has emerged as a viable platform to provide an alternative way of financing without the help of traditional intermediaries such as banks. However, P2P lending platforms have experienced risks in China, and previous research mainly focuses on using subjective methods for constructing and assessing the risk index system of P2P platforms. We propose a novel approach to establishing a risk index system based on previous research and real-world data, selected using correlation analysis and principal component analysis. Moreover, the entropy-revised G1 combination method has been used in this paper to assess the risk performance of P2P lending platforms, with both expert knowledge and real-world data taken into account. In this paper, we use information contribution to show the constructed risk index system is valid. In addition, we rank the ninety-two P2P lending platforms based on their calculated risk evaluation scores, which are further tested with the ranking offered by China’s rating agency using Spearman’s coefficient. Testing results show the proposed risk assessment for P2P platforms in China is rational and efficient, giving us unique insight into how to evaluate the risk performance of P2P platforms, and thus can be used by regulators to better supervise these platforms in China.

Research on Risk Factors Identification of P2P Lending Platforms

We take 2259 P2P Lending platforms as the sample, and integrate 14 variables from five dimensions to analyze the risk factors of P2P Lending problematic platforms by binary logistic model. The empirical results show that the 11 variables which are the type of company, platform background, operation time, the type of project, interest rate, fund custody, term of loan, day-bid, transfer of creditor’s rights, automatic bidding and information disclosure, have significant influences on the operating status of the platform, while the other variables such as registered capital, the number of employees and security mechanism have no obvious impact on the operating status of the platform. The results provide a reference for investors and regulators.

GBDT-SVM Credit Risk Assessment Model and Empirical Analysis of Peer-to-Peer Borrowers under Consideration of Audit Information

With the rapid development of P2P (peer-to-peer) online lending industry, how to effectively evaluate the borrowers’ credit risk in the platform has drawn more and more attention. In this paper, we propose a borrower credit risk assessment index system that includes basic information, work information, credit information, asset information, loan information and audit certification information, and come up with a credit risk assessment model that combines Gradient Boosting Decision Trees (GBDT) and support vector machine (SVM). Then, we select the data of P2P lending platform to carry out the empirical analysis of the credit risk assessment, and compare with the common four kinds of single prediction models such as logic regression (LR), artificial neural network (ANN), SVM and clustering algorithm. The results show that the increase of audit certification information helps to improve the forecasting effect of the model, and the credit risk assessment model of P2P lending platform based on GBDT and SVM has higher prediction accuracy and stability.

Optimal Stackelberg strategies for financing a supply chain through online peer-to-peer lending

In recent years, supply chain finance (SCF) through online peer-to-peer (P2P) lending platforms has gained its popularity. We study an SCF system with a manufacturer selling a product to a retailer that faces uncertain demand over a single period. We assume that either the retailer or the manufacturer faces a capital constraint and must borrow capital through an online P2P lending platform. The platform determines a service rate for the loan, the manufacturer sets a wholesale price for the product, and the retailer chooses its order quantity for the product. We identify optimal Stackelberg strategies of the participants in the SCF system. For an SCF system with a capital-constrained retailer, we find that the retailer's optimal order quantity and the manufacturer's optimal wholesale price decrease with the platform's service rate. For an SCF system with a capital-constrained manufacturer, we find that as the platform's service rate increases, the manufacturer's optimal wholesale price increases but the retailer's optimal order quantity decreases. Our analysis suggests that it is important for the retailer and the manufacturer to take the online P2P lending platform's financial decisions (such as the service rate) into account when making their operational decisions.

Loan default prediction by combining soft information extracted from descriptive text in online peer-to-peer lending

Predicting whether a borrower will default on a loan is of significant concern to platforms and investors in online peer-to-peer (P2P) lending. Because the data types online platforms use are complex and involve unstructured information such as text, which is difficult to quantify and analyze, loan default prediction faces new challenges in P2P. To this end, we propose a default prediction method for P2P lending combined with soft information related to textual description. We introduce a topic model to extract valuable features from the descriptive text concerning loans and construct four default prediction models to demonstrate the performance of these features for default prediction. Moreover, a two-stage method is designed to select an effective feature set containing both soft and hard information. An empirical analysis using real-word data from a major P2P lending platform in China shows that the proposed method can improve loan default prediction performance compared with existing methods based only on hard information.

FinTechs in China – with a special focus on peer to peer lending

PurposeChina is a country with the most number of operating peer-to-peer (P2P) lending platforms (approximately 2,000) worldwide. This study aims to provide an overview on FinTechs in China. It was examined why payment services and P2P lending are so popular in China and what are the determinants for the emergence of P2P lending platforms in different provinces in China.Design/methodology/approachThis study conducted a descriptive analysis of P2P lending in China and an empirical analysis of determinants of P2P lending in China.FindingsThis descriptive analysis shows that the surge in the number of the P2P platforms in China follows an inverted U-shaped phenomenon. However, the outstanding balances of P2P lenders is still increasing, while average yields of P2P lenders have sharply plunged. The empirical findings indicate that P2P lending is more extensive in the region with more mobile phone subscriptions; outstanding balance of P2P lenders in region is negatively associated with the size of traditional banking sector; and the number of the P2P platforms in negatively related to the fixed assets investments in region, whereas average yield is positively associated with the fixed assets investments.Originality/valueCurrently, almost no research papers with empirical analysis of FinTechs, especially P2P lenders, exist. This study estimates a simple model to find determinants of P2P lending.

The persuasion of borrowers’ voluntary information in peer to peer lending: An empirical study based on elaboration likelihood model

This paper investigates the persuasive process of borrowers' controllable voluntary information which can be easily manipulated and is particularly valuable for borrowers to persuade lenders and enhance the likelihood of funding success in P2P lending marketplace. Using a large scale data set from a Chinese leading P2P lending platform, namely Renrendai, based on a dual-processing persuasion theory-Elaboration Likelihood Model, we introduce four newly persuasive features (Completeness, Sentiment, Language intensity, The number of certificates) with central and peripheral cues in voluntary information. The results show that the persuasion of borrowers' voluntary information can be accomplished via two distinct routes in P2P lending, suggesting that not only central cues but also peripheral cues have significant effect on lenders’ decision making. Specially, negative sentiment is negatively associated with funding success which is contradictory to the findings in fund-raising appeals say using negative emotions can evoke “empathy-helping”. Moreover, we find a negative interaction effect on funding success between Completeness and The number of certificates. Our study shed some light for deeply understanding the dual-route persuasive process in P2P lending.

P2P Lending Survey

P2P lending is an emerging Internet-based application where individuals can directly borrow money from each other. The past decade has witnessed the rapid development and prevalence of online P2P lending platforms, examples of which include Prosper, LendingClub, and Kiva. Meanwhile, extensive research has been done that mainly focuses on the studies of platform mechanisms and transaction data. In this article, we provide a comprehensive survey on the research about P2P lending, which, to the best of our knowledge, is the first focused effort in this field. Specifically, we first provide a systematic taxonomy for P2P lending by summarizing different types of mainstream platforms and comparing their working mechanisms in detail. Then, we review and organize the recent advances on P2P lending from various perspectives (e.g., economics and sociology perspective, and data-driven perspective). Finally, we propose our opinions on the prospects of P2P lending and suggest some future research directions in this field. Meanwhile, throughout this paper, some analysis on real-world data collected from Prosper and Kiva are also conducted.

English

Online peer-to-peer (P2P) lending is a nascent but burgeoning marketplace that is expected to transform the landscape of the finance industry. Although, this topic is crucial, studies on the performance of individual investors in the P2P lending marketplace are few. The majority of P2P lending platforms add more intermediation or platform-based investment to improve product offerings and market efficiency. However, research on the performance of those different types of “re-intermediation” is limited. A unique and complete dataset from PPDai.com indicates that almost 95% of individual investors on the online peer-to-peer lending market generally do not obtain returns commensurate to the amount of systematic risks they assume. The performance of the different types of “re-intermediation”, such as portfolio tools and financial products, is not statistically distinguishable from that of the market. Nevertheless, the returns of these “re-intermediation” are less volatile, which shows most individuals can benefit from these types of “re-intermediation”. Key words: Peer-to-peer lending, performance, individual investor, re-intermediation.

How Incentive Structure Affects the Effectiveness of Referral Strategy: Evidence from a Randomized Field Experiment on a Lending Platform

Large and high quality user base is an important determinant of firm performance. Firms spend a great amount of resources in building referral programs to grow user base. Yet, substantial variations exist in the effectiveness of these referral programs with various incentive structures. We argue that the extent to which referral programs can grow user base depends on how existing users evaluate the cost and benefit of their referral behavior. Using a large-scale randomized field experiment with around one hundred thousand participants on one of the largest P2P lending platforms in China, we find that referral programs structured as self-benefit (egoistic) appeal or other-benefit (altruistic) appeal significantly reduce the number of new users brought by the existing users but new users from other-benefit appeal made more investment. Our study demonstrates that under certain circumstances, these referral programs structured as egoistic or altruistic incentive structure may backfire.

The role of punctuation in P2P lending: Evidence from China

This paper investigates the role of punctuation in the peer-to-peer (P2P) lending market. Using data from Renrendai, one of the largest P2P lending platforms in China, we investigate how the amount of punctuation used in loan descriptions influences the funding probability, borrowing rate, and default. The empirical evidence shows that the amount of punctuation is negatively associated with the funding probability and borrowing rate. We propose that the usage of punctuation affects the readability of a loan description and reflects borrowers’ self-control and cognitive ability. Within a given number of words, excessive usage of punctuation makes loan description informal and reduces the readability of the text, thereby impairing investors’ trust in borrowers. Moreover, borrowers that overuse punctuation may have lower ability of self-control, and tend to underestimate the risk of borrowing and offer lower borrowing rate due to overconfidence.

The Research of Recommendation Algorithms in P2P Lending

With the rapid development of P2P lending in China In recent years, how to recommend bid projects to the bidder to meet its preferences will become a research hotspot, but there are few studies in this area. And since the P2P lending platform is not a dominant scoring mechanism, it is an urgent need to solve the problem of how to generate a reasonable score matrix. First of all, from the PPDai.com to climb over more than 320 thousand tenders of the last two years. Then, based on the deeply analysis of the data characteristics of the P2P lending areas, three types of different types of scoring matrix (Boolean, continuous and mixed) are generated. Then, three kinds of classical collaborative filtering recommendation algorithms are used in the experiment. The results show that the performance of the recommendation algorithm has important influence on the performance of the recommendation algorithm, and the performance of cooperative filtering algorithms is different in P2P lending compared with in some other areas. Finally, the experimental results are analyzed, and the relevant suggestions are given for the P2P lending areas.

Research on the Credit Risk Assessment of Chinese Online Peer-to-peer Lending Borrower on Logistic Regression Model

Starting from the perspective of borrower credit risk in online peer-to-peer lending, the paper first collected the relevant borrowers’ data sample from Paipai Lending, a well-known online P2P (peer-to-peer) lending platform in China. By using Information Gain technique, the paper screened out the ultimate indicator variables from the original sample and then constructed a credit risk evaluation model of Chinese Online P2P Lending borrower based on Logistic Regression. Finally, the paper transferred the groups of testing sample set into the model to test the model accuracy. By comparing the model’s results with the relevant actual defaults, the model is proved to have good explanatory power for the credit risk of borrower.

Research on the Credit Risk Assessment of Chinese Online Peer-to-peer Lending Borrower on Logistic Regression Model

Starting from the perspective of borrower credit risk in online peer-to-peer lending, the paper first collected the relevant borrowers’ data sample from Paipai Lending, a well-known online P2P (peer-to-peer) lending platform in China. By using Information Gain technique, the paper screened out the ultimate indicator variables from the original sample and then constructed a credit risk evaluation model of Chinese Online P2P Lending borrower based on Logistic Regression. Finally, the paper transferred the groups of testing sample set into the model to test the model accuracy. By comparing the model’s results with the relevant actual defaults, the model is proved to have good explanatory power for the credit risk of borrower.