Chinese P2P Lending Platforms Research Articles

Ensemble methods for credit scoring of Chinese peer-to-peer loans

Risk control is a central issue for Chinese peer-to-peer (P2P) lending services. Although credit scoring has drawn much research interest and the superiority of ensemble models over single machine learning models has been proven, the question of which ensemble model is the best discrimination method for Chinese P2P lending services has received little attention. This study aims to conduct credit scoring by focusing on a Chinese P2P lending platform and selecting the optimal subset of features in order to find the best overall ensemble model. We propose a hybrid system to achieve these goals. Three feature selection algorithms are employed and combined to obtain the top 10 features. Six ensemble models with five base classifiers are then used to conduct comparisons after synthetic minority oversampling technique (SMOTE) treatment of the imbalanced data set. A real-world data set of 33 966 loans from the largest lending platform in China (ie, the Renren lending platform) is used to evaluate performance. The results show that the top 10 selected features can greatly improve performance compared with all features, particularly in terms of discriminating bad loans from good loans. Moreover, comparing the standard

Determinants of defaults on P2P lending platforms in China

Chinese P2P lending platforms have an astonishing default rate of 87.2% based on data available in 2019, which indicates the seriousness of the problem this industry faces. Insufficient regulation has resulted in generation of risky services, such as margin finance in 2015 for stock markets and zero down-payment mortgages in 2016 for real estate buyers. Such services are prone to resulting in dramatic losses to investors with the following potential causes: adverse selection caused by information asymmetry of the P2P platform operators, lack of financial knowledge or expertise of the investors, insufficient regulation on P2P platforms, and changes in policies related to stock and real estate markets.Does “Too Big to Fail” (TBTF) apply to Peer-to-peer (P2P) lending platforms in China? Are platforms with large Transaction Volumes or large Total Loan Size safer? This paper aims at answering such questions and identifies other factors that have led to defaults of such P2P lending platforms. In order to generate a more robust model that covers a wider range of factors, we adopt two approaches: Failure Prediction Model and Decomposition Methods. The reason why we have adopted this approach was that the factors that caused failure of such P2P platforms were very complicated and varied in nature. Failure Prediction Model is mainly based on the disclosed transaction or financial data. However, Decomposition Method aims at identification of sources of problem from different groups of factors, such as internal operations and external business environment. Also, another contribution of our research is that the data sets that we have used are from three different sources, which provide us a more comprehensive picture about the risks faced by such P2P lending firms.This study provides evidence that the bond yield, which reflects the liquidity level of the market, is the major reason for P2P platforms’ failure during the research period. Our results also indicate that apart from the size-related factors one also needs to answer the question - “Were platforms with larger Transaction Volumes and Total Loan Sizes safer?” The style factors like the interest rate and ownership, the timing factors like loan maturity and bond yield, and the selectivity factors like popularity are found to be even more significant. Hopefully, our findings could contribute academically to the existing literature in the credit risk estimation of online P2P lending platforms and provide practical support for development of a more effective risk monitoring system for online P2P lending platforms.

Message framing in P2P lending relationships

This paper investigates whether language and associated message framing (low-cost signal) can provide a solution to the risks generated by asymmetric information in P2P lending, drawing on the signalling and message-framing theories. First, it examines the extent to which message framing is associated with funding outcomes in the context of P2P lending; second, it investigates whether positive message framing reinforces the positive impact of credit ratings (high-cost signal) on funding outcomes. Our analysis is conducted on a dataset of 33,028 listings of potential borrowers from a Chinese P2P lending platform using the Heckman selection models. We find that the use of positively framed messages is positively associated with positive funding outcomes and enhances the positive impact of the credit ratings on funding outcomes. Our results contribute to the literature on the effectiveness of low-cost signals in of Internet-based interactions while highlighting complementarities between different types of signals in P2P lending.

Can Readability of Loan Description Affect Loan Success Rate and Loan Cost?: A Textual Analysis of P2P Loan Description

Text is an important form of information transfer. In a P2P (Peer-to-Peer) loan market with severe information asymmetry, loan descriptive information voluntarily written by a borrower may generate significant influence on investors’ decision-making. As an important language feature, readability determines whether the audience can accurately identify textual contents. To discuss the influence of readability of loan description on borrowing behaviors, the data of a Chinese P2P lending platform Renrendai during 2013–2017 were used in this study. Readability index of loan description was constructed through the textual analysis method, followed by an empirical verification of the influences of readability of loan description on loan success rate and loan cost. Results indicate that the readability of loan description in China’s P2P loan market can generate incremental information, and the readability of loan description has evident nonlinear relations with loan success rate and loan interest rate. Moreover, the readability of loan description presents a “reverse U-shaped” relation with loan success rate and a “U-shaped” relation with loan interest rate. Demographic information (gender and educational background) of borrowers will not influence investors’ feedback behaviors toward the readability of loan description. Conclusions provide empirical evidence for standardizing loan descriptive information on P2P lending platforms.

Are All Heuristics Created Equal? Evidence from P2P Investments

Heuristics have a ubiquitous influence on decision-making. Despite a large strand of literature on various heuristics, scant research addresses the concurrent applications of different heuristics or the interplay amongst them. Using detailed peer-to-peer (P2P) investment data from Renrendai, a leading Chinese P2P lending platform, we make the first attempt to uncover the relationship between two important numerological heuristics: the round-number heuristic and the lucky-number heuristic. We document a substitution relationship between these two heuristics. The selection of round numbers versus lucky numbers for the loan amount reveals borrowers’ credit quality and affects the loan funding success rate, though the ex post performance of funded loans is similar. Lenders also apply heuristics in setting the bid amount, which potentially reveals information about their activeness and risk preference. As lenders become more experienced, they form more sophisticated judgments about the loan quality from borrowers’ use of heuristics. Overall, our paper examines the heterogeneities and interlacing of heuristics by establishing a framework to extract information about individuals’ characteristics and preferences from the heuristics they use. Our findings are generalizable to many other real-life situations.

Borrower Learning Effects: Do Prior Experiences Promote Continuous Successes in Peer-to-Peer Lending?

There are a large amount of studies on the impact of individual experience on learning outcome, which ignore the conditioning and implicitly assume that the learning behaviors are bound to arise. This study develops a two-stage conceptual model for the interpretation of individual learning, and aims to explore how individual’s prior experience affects the initiating of subsequent learning behavior first and then impacts the success of subsequent learning behavior. Using a large sample of loan application data over a five-year period from a Chinese P2P lending platform Renrendai, we found strong evidence that both prior successes and prior failures can motivate borrowers to take subsequent borrowing behaviors again. However, in regard to the impact of individual experience on learning outcome, our finding in online environment is contrary to the prevalent view in organizational learning—“we learn more effectively in failure than in success”. Specifically, we found only successes can lead to desirable success whereas failures can’t, which indicates that borrowers with failure experience are willing to repeat borrowing but unable to learn from their failures. Further, we find a beneficial interaction effect between borrower’s prior successes and prior failures on subsequent borrowing success. These results are robust across a variety of settings. Our study enriches the understanding of individual learning by focusing not only on outcome improvement but also on conditioning. Moreover, we investigate learning process in an online environment which is anonymous and lack of peer communication that offline organizations have, we draw some different findings. Our findings also offer practical insights for borrowers under financial difficulties and platform managers to correctly interpret prior experience and enhance the probability of subsequent funding success in P2P lending.

Will CEOs with banking experience lower default risks? Evidence from P2P lending platforms in China

Using a novel dataset of 121 Chinese P2P lending platforms, we investigate the impact of CEOs’ banking experience on default risk. The empirical results indicate that CEOs with prior banking experience manage default risk better. Moreover, CEOs’ banking experience has a stronger influence on small platforms and in situations where the platforms’ depository banks are city commercial banks. Our results indicate that although fintech provides technology to reduce risks, we cannot ignore the constructive role of professional experience in risk management. Thus, investors and regulators in emerging markets should pay attention to managers’ financial qualifications, and especially to CEOs’ banking experience.

Building investor trust in the P2P lending platform with a focus on Chinese P2P lending platforms

As massive Chinese P2P platforms have failed dueto moral risk and liquidity risk, which decreased investorsconfidence in P2P lending, the major question facing the futuregrowth of P2P platforms is how to best build investors trust. This study was based on the elaboration likelihood model andexamines how to persuade investors to develop initial trust inP2P platform. The empirical analysis results support the financialand credit status of P2P platforms are key elements in buildingthe trust of investors. The social capital, risk management, andoperating duration provide the necessary support to increase thenumber of platform investors. The average interest rate and thedisclosure of information by the borrowers does not significantlyaffect the number of platform investors. These findings willfacilitate future development efforts for p2p lending and therational investments of investors.