借款描述对互联网金融信用风险的影响研究

陈为民; 杨泽俊; 陈 依

借款描述对互联网金融信用风险的影响研究

引用本文：陈为民，杨泽俊，陈依.借款描述对互联网金融信用风险的影响研究[J].财经理论与实践,2022,(6):24-30

摘要点击次数: 252

全文下载次数: 0

作者	单位
陈为民，杨泽俊，陈依	（湖南科技大学商学院，湖南湘潭 411201）

中文摘要:基于互联网金融提供的客户借款描述，通过潜在语义分析挖掘借款描述文本内容的主题，运用二元分位数回归分析借款描述对互联网金融信用风险的影响。实证结果表明，借款描述中有关情感表达、个人信用和借款目的的描述与违约情况呈负相关，有关财务情况的描述与违约情况呈正相关。

中文关键词:互联网金融二元分位数回归潜在语义分析文本挖掘

The Influence of Loan Description on Credit Risk of Internet Finance

Abstract:Based on the customer loan description provided by Internet finance, the binary quantile regression method is used to classify the text content in the loan description of the lending platform and the data obtained by content mining according to the latent semantic analysis(LSA), and the impact of the loan description on the credit risk of Internet finance is considered. The results show that the description of emotional expression, personal credit and borrowing purpose in the loan description is negatively correlated with the default, and the description of the financial situation is positively correlated with the default.

keywords:Internet finance binary quantile regression LSA text mining

查看全文 查看/发表评论 下载pdf阅读器