Font Size: a A A

Research On Credit Risk Evaluation Of P2P Lending In China

Posted on:2017-04-19Degree:MasterType:Thesis
Country:ChinaCandidate:F F ZhaoFull Text:PDF
GTID:2309330488952371Subject:Applied statistics
Abstract/Summary:PDF Full Text Request
In 2006, China established the first P2P network lending site-pat loan. After a few years, the P2P network lending platform rarely involved. Until 2011 the P2P network lending industry before entering a period of rapid development. Since 2013,P2P platform is almost every day a rapid expansion of the speed. According to the 2015 China Internet lending industry annual report shows that as of the end of 12 2015, P2P net loan industry operating platform reached 2595. P2P net loan in 2015 full year turnover reached yuan, compared to the year 2014 net loan volume (252 billion 800 million yuan) increased by 288.57%.Relative to the explosive growth in 2013, since September 2013 began to focus on P2P lending platform appeared closures, a large number of problems emerged platform. Domestic P2P platform only in 2015 the full year closure, foot, reflecting the difficulties and other issues platform to reach 896, is 3.26 times in 2014. In our 2595 P2P network lending platform, the majority of the platform borrowing rates are higher than the same period the bank loan interest rates, and some even reached 4 times the same period the bank rate. Because many P2P loan borrowers are weak anti risk ability of the natural person, especially unreasonable debt structure of the borrower to funding constraints, overdue and rollover phenomenon, although the rapid development of the P2P network lending brought the bonus system innovation, but also bring the enormous social risks.Based on this, this article from the credit point of view, the study of P2P network lending in the borrower’s credit risk, the 365 easy credit published by the borrower information as a source of data, as a source of data information. Also refer to the personal risk evaluation system of commercial banks index selection is selected out several alternative indicators, through data processing, classification and quantification method, the index modeling regression, then gender, age, monthly income, overdue repayment pen number, the term of the loan, the annual interest rate and whether default a positive correlation; marital status, cultural degree, whether to have owned housing, on time repayment amount of negative and whether default a positive correlation, the nature of the unit, the successful loan number, loan amount, loan purpose and whether the default has no significant correlation.
Keywords/Search Tags:P2P network loan, borrower, credit risk assessment, Logit regression
PDF Full Text Request
Related items