Research On Risk Identification And Operational Efficiency Of P2P Lending Platforms In China

In recent years,as a new internet financial loan model,P2P(Peer to Peer)lending develops rapidly in China,but problems occur frequently.Especially in the second half of 2018,the risk of P2P lending industry was concentrated,and the security of P2P platforms has become the focus of all the stakeholders.Therefore,how to identify the security of P2P platforms and evaluate the operational efficiency of P2P platforms has great value on the healthy development of the P2P lending industry.In this paper,the overall security and operational efficiency of P2P platforms is considered seriously,the Random Uniform Forests(rUF)algorithm is applied for constructing the risk identification model of P2P platforms,and degree of importance of various factors which influence the risk identification of P2P platforms is debated based on the variable importance theory of Random Uniform Forests.And the DEA method is used to evaluating the operational efficiency so as to identify relatively efficient and inefficient P2P platforms in China.Results show that ensemble learning algorithms are more effective in risk identification compared to the single traditional classification algorithms;Some indicators such as Operation Time,Average Rate,Contributed Capital,the Number of Followers,Internet users' impression play important roles in risk identification of P2P platforms;The interest rate has a strong correlation with the high-risk platforms,and the platforms' security mode has little impact on the high-risk platforms and the low-risk platforms.The overall operating level of China's P2P lending platforms is not high,and the technical efficiency level of most platforms is low,which affects its comprehensive efficiency level.The study in this paper is helpful to investors to make reasonable investment decisions and could reduce risks and losses caused by information asymmetry;It's also beneficial for platforms to strengthen industry self-regulation and achieve healthy and continual operations.