A decision support model for investment on P2P lending platform

Abstract

Peer-to-peer (P2P) lending, as a novel economic lending model, has triggered new challenges on making effective investment decisions. In a P2P lending platform, one lender can invest N loans and a loan may be accepted by M investors, thus forming a bipartite graph. Basing on the bipartite graph model, we built an iteration computation model to evaluate the unknown loans. To validate the proposed model, we perform extensive experiments on real-world data from the largest American P2P lending marketplace—Prosper. By comparing our experimental results with those obtained by Bayes and Logistic Regression, we show that our computation model can help borrowers select good loans and help lenders make good investment decisions. Experimental results also show that the Logistic classification model is a good complement to our iterative computation model, which motivates us to integrate the two classification models. The experimental results of the hybrid classification model demonstrate that the logistic classification model and our iteration computation model are complementary to each other. We conclude that the hybrid model (i.e., the integration of iterative computation model and Logistic classification model) is more efficient and stable than the individual model alone.

Investment Decisions and Investor Experience in Choosing Financial Technology (Fintech) Services: Peer-To-Peer Lending

“…There are several theories that explain financial behaviour which are herding theory, anchoring theory, regret theory and prospect theory. Herding theory illustrates the behaviour of investors who are very dependent on the opinions of other investors [21]. Whereas Anchoring theory explains the behaviour of investors who depend heavily on a data or information obtained without taking into account the accuracy of the source [22].…”

“…Even the results of recommendations from colleagues who are known to have a greater influence than the information that has been listed [9]. This happens because investors tend to have herding behaviour [21], which is an attitude that considers the information owned by others better because they have previous experience. This information is taken into consideration for investors to conduct a more in-depth evaluation, especially related to the business mechanism of P2PL (table 1).…”

InvierteCampo: propuesta de prototipo de S.W. para obtención de crédito orientada a agricultores de frijol en Zacatecas, utilizando P2P Lending

“…En una plataforma de igual a igual, deberá saber si esta plataforma es compatible con el tipo de préstamo que desea. [10,11] Como prestatario, deberá proporcionar una amplia información antes de recibir el dinero. Su puntaje de crédito también determinara que tipo de interés recibe, como en cualquier otro prestamista.…”

Application of Instance-Based Entropy Fuzzy Support Vector Machine in Peer-To-Peer Lending Investment Decision

“…Various models have been developed to enhance the profitability in P2P lending market. For example, Serrano-Cinca et al [30] discovered the factors explaining defaults in P2P lending based on a hypotheses test and a survival analysis; Jiang et al [10] extracted features from the descriptive loan text with latent Dirichlet allocation (LDA) model and predicted defaults in P2P loan using the soft information; and Zeng et al [31] attempted to form a bipartite graph between loans and investors and built an iteration computation approach to develop an investment decision model. Since the P2P lending is similar to credit scoring, the literatures of the development of credit scoring are a decent precedent for the study in P2P lending [32]- [39].…”