摘要
得益于大数据、云计算等互联网技术的成熟,以跨期还款为借款人提供信贷等金融服务为特征的互联网消费金融机构迅速发展,相应地企业信用风险问题也愈发突出。如何度量信用风险成为了企业健康持续发展的关键。本文以人人贷的真实借贷记录为数据,构建二元Logit模型对借款人信用风险进行度量和预测。实证表明,借款人基本信息、借款标的以及贷款信用初评等对企业的信用风险有显著影响,Logit模型在预测违约概率上具有较高的准确性与稳定性。
Benefiting from the maturity of internet technologies such as big data and cloud computing,internet consumer financial institutions featuring inter-period repayment to provide borrowers with credit and other financial services have developed rapidly,and corporate credit risks have become increasingly prominent.How to measure credit risk has become the key to the healthy and sustainable development of an enterprise.This paper uses the real loan records of Renrendai as data,and builds a binary Logit model to measure and predict the credit risk of borrowers.Empirical evidence shows that the borrower’s basic information,the subject of the loan and the initial credit rating of the loan have a significant impact on the credit risk of the enterprise,and the Logit model has high accuracy and stability in predicting the probability of default.
出处
《工程经济》
2022年第2期28-35,共8页
ENGINEERING ECONOMY
基金
2020年度江苏省社科基金项目《疫情冲击背景下政府审计促进金融服务普惠经济的实现路径研究》(编号:20GLB021)的阶段性成果
