P2P网贷违约人是否具有区域性特征——来自湖南省的例证

Whether the Network Loan Defaulters Have Regional Characteristics——An Evidence from Hunan Province

借助网络爬虫技术手段获取"人人贷"平台上借款人的各项信息,提取两个样本:分为全国随机样本和湖南省随机样本,构建二元Logit回归模型,分析其中对违约率有显著影响的变量.研究表明,负债收入比、借款期限、学历、房产、房贷、描述指数对违约行为有负向影响,而借款利率、车产、认证个数对借款者违约行为有正向影响.同时,通过对两个样本最终回归模型的比较,发现湖南省违约人特征与全国随机样本中体现的违约人特征基本一致,但其中较为特殊的是,在湖南拥有房产和车产不能作为网络借款人履约能力提升的标志.

This paper obtains the information of the borrowers on the "renrendai"net loan platform with the help of the web crawler technology佲 and extracts two samples丗 the random samples of the whole country and the random samples of Hunan province. A binary Logit regression model is built to analyze the variables which have significant influence on the default rate. The study shows that the debt-to-income ratio, the maturity of the loan, the educational background, the property佲 the mortgage and the description index have a negative impact on the default behavior, while the interest rate of the loan, owning cars and the number of certification have a positive impact on the default behavior of the borrowers. At the same time, through the comparison of the final regression model of two samples, it is found that the characteristics of the defaulters in Hunan province is basically consistent with the random samples of the whole country佲 but e*specially the ownership of real estate and car can not help to improve the performance of network borrowers in Hunan.