Best classification algorithms in peer-to-peer lending

A proper credit scoring technique is vital to the long-term success of all kinds of financial institutions, including peer-to-peer (P2P) lending platforms. The main contribution of our paper is the robust ranking of 10 different classification techniques based on a real-world P2P lending data set. Our data set comes from the Lending Club covering the 2009–2013 period, which contains 212,252 records and 23 different variables. Unlike other researchers, we use a data sample which contains the final loan resolution for all loans. We built our research using a 5-fold cross-validation method and 6 different classification performance measurements. Our results show that logistic regression, artificial neural networks, and linear discriminant analysis are the three best algorithms based on the Lending Club data. Conversely, we identify k-nearest neighbors and classification and regression tree as the two worst classification methods.     

Applying the counseling-learning approach to a tourism-related massive open online course

ABSTRACT

This study discusses how to apply counseling-learning (CL) principles to a particular e-learning solution for teaching a tourism-related subject via a massive open online course (MOOC). Several effective caring patterns in achieving learning-related goals and being part of a community according to the CL principles are presented and discussed using the MOOC “eTourism: Communication Perspectives” as a case study. The study underlines how the MOOC platform can act as a place for contents enjoinment and active learning. Moreover, the active role of social media for increasing the engagement of learners in the proposed activities and for developing a sense of the community is identified. In particular, Facebook and Twitter can act as places for community building and informal social interactions among learners that last beyond the completion of the course, which in turn can be a valid aid for continuing the relationships among instructors/learners and learners/learners, and for reaching new ones.     

The signaling effects of education in the online lending market: Evidence from China

In this study, we use data from an online lending platform named Xinxindai in China to empirically study the signaling effects of education for the default risk of borrowers. Three dependent variables are created, namely, the probability of default, overdue payments and overdue amount, and probit models, count models and Tobit models are employed correspondingly. The number of universities in the “211 Project” of China at the city level is employed as the instrumental variable. The empirical evidence shows that education generally plays a strong signaling role in the identification of borrowers’ default risk in China. The negative marginal effect of education declines as borrowing times increase and as the marketization of regions deepens. This study helps to fill an important gap in the existing literature. Platforms and lenders can use educational level for reference in identifying the default risk of borrowers.     

Will FinTech make regional banks superfluous for small firm finance? Observations from soft information-based lending in Germany

Regional banks have a competitive advantage in that short distances to clients enable the use of soft information for superior lending decisions. If the ambition of FinTech start-ups to create superior screening and monitoring technologies materialises, this advantage would be diminished and regional banks would become superfluous for small firm finance. To explore this claim, the paper in hand analyses qualitative empirical data about the lending processes and rating system use of regional German savings banks. In essence, the results from participant observation and interviews clarify the importance of “real” soft information for critical lending decisions. The context specificity and limited verifiability of “real” soft information hamper it from being hardened through the use of rating systems and other bank-ICT. Though FinTech's scoring technologies may overcome the first limitation, it appears likely that in the course of scoring development “real” soft information will be systematically crowded out due to the manipulation problem. The paper expects improved access to finance for SMEs if FinTech solutions overcome both limitations of “real” soft information use, or if peer-to-peer lending and regional banks coexist. Deteriorated access to finance is expected if FinTech companies displace the relationship banking of regional banks due to enhanced competition, without preserving the advantages of “real” soft information with superior screening and monitoring technologies. The paper concludes with recommendations on how to prevent deteriorated access to finance for small firms by promoting fair competition and FinTech innovations.     

Market response to syndicated loan announcements from high-profile failed and acquiring banks during the global financial crisis

Previous studies that have examined the impact of the 2008 financial crisis on syndicated loans have ignored potential differences between lending banks by explicitly or implicitly aggregating all lenders together and focusing on borrower characteristics. One must jointly consider both borrower and lender to fully understand the complex role of the syndicate during this period. We consider the identity of the lender, with a focus on five major US banks that failed and their five corresponding acquirers. Our results highlight the distinct roles of investment and commercial banks and facilitate an understanding of relationship and transactional-based lending.     

The influencing factors of satisfaction and lending intention in online lending investment: an empirical study based on the Chinese market

This paper develops a platform‐based influencing factors model which considers value perception, risk prevention measure, non‐default experience, trust and incentive gap, to better examine the impact of platforms on investors’ satisfaction and lending intention based on the Chinese market. The results reveal that the first four factors positively influence the satisfaction of the investors, while the incentive gap has a negative impact, and there is a positive association between investors’ satisfaction and lending intention. Some specific features of China’s online lending market are identified, which provides valuable insights for online lending platforms and the government.     

互联网视角下供应链金融的新发展

在这个网络社会愈发深化的时代,通过互联网科技完善和发展线上供应链金融成为必要的发展方向。本文首先梳理了传统供应链金融的基本模式,发现了其存在的不足;然后重点介绍了当前三种主要的线上供应链金融模式,总结了线上供应链金融的优势;最后,提出相关政策建议,认为金融机构应该不断升级线上供应链金融产品,逐步完善供应链金融线上操作系统,监管机构需要出台更加严格的监管规则对线上供应链金融进行有效监管。     

The mechanism of credit risk contagion among internet P2P lending platforms based on a SEIR model with time-lag

The credit risk contagion of Internet peer-to-peer (P2P) lending platforms is an important part of Internet financial risk management and supervision. This study analyzes the contagion path of credit risk in Internet P2P lending. Based on complex network theory and the theory of infectious disease dynamics, the characteristics of Internet P2P lending development are combined to construct a SEIR model of credit risk transmission among Internet P2P lending platforms with time lag, and the robustness of the model is analyzed and proven. The influence of platform correlations, the susceptible immune rate, the platform elimination rate, contagion latency, the saturation coefficient, and the susceptibility input rate on credit risk contagion behavior among Internet P2P lending platforms is analyzed, using the equilibrium point and threshold value. The impact of each variable is analyzed by simulation. Corresponding countermeasures and suggestions are proposed to prevent and control credit risk contagion among these platforms.     

Lock‐In Effects in Relationship Lending: Evidence from DIP Loans

Do prior lending relationships result in pass‐through savings (lower interest rates) for borrowers, or do they lock in higher costs for borrowers? Theoretical models suggest that when borrowers experience greater information asymmetry, higher switching costs, and limited access to capital markets, they become locked into higher costs from their existing lenders. Firms in Chapter 11 seeking debtor‐in‐possession (DIP) financing often fit this profile. We investigate the presence of lock‐in effects using a sample of 348 DIP loans. We account for endogeneity using the instrument variable (IV) approach and the Heckman selection model and find consistent evidence that prior lending relationship is associated with higher interest costs and the effect is more severe for stronger existing relationships. Our study provides direct evidence that prior lending relationships do create a lock‐in effect under certain circumstances, such as DIP financing.