A Good Sketch is Better than A Long Speech: Evaluate Delinquency Risk through Real-Time Video Analysis 眼见为实:基于实时视频分析的信贷违约风险研究

时间:2022-11-29         阅读:

光华讲坛——社会名流与企业家论坛第6360

主题A Good Sketch is Better than A Long Speech: Evaluate Delinquency Risk through Real-Time Video Analysis 眼见为实:基于实时视频分析的信贷违约风险研究

主讲人新南威尔士大学商学院 戴理理副教授

主持人亚搏官方(中国)责任有限公司财税学院 李子燃副教授

时间12月2日 10:00-11:30

举办地点:腾讯会议,会议ID:260-932-147

主办单位:财税学院 科研处

主讲人简介:

戴理理,新南威尔士大学商学院的会计学副教授。他的研究兴趣是资本市场的会计、审计和金融研究。他的著作发表在Journal of Accounting Research, Review of Financial Studies, Review of Accounting Studies, European Accounting Review, Journal of Business Finance and Accounting, Journal of Corporate Finance,和Journal of Banking and Finance.同时,他兼任Accounting and Finance编委.

内容提要:

In this paper, we adopt an innovative strategy to assess borrowers’ creditworthiness in consumer credit markets. This new assessment strategy applies machine-learning based analyses on real-time video information that records borrowers’ behavior during the loan application process. We find that the extent of borrowers’ facial expressions of happiness is negatively associated with the likelihood of future loan delinquency. In contrast, such delinquency likelihood increases with the degree of fear expressions. These results are consistent with two economic channels relating to the adequacy and uncertainty of borrowers’ future income, drawn from the extant psychology and economics literature. Our study provides important practical implications for marketplace lenders and policymakers.

在本文中,我们采用了一种创新的策略来评估消费信贷市场中借款人的信誉。这种新的评估策略应用了基于机器学习的实时视频信息分析,记录了贷款申请过程中借款人的行为。我们发现,借款人面部表情的快乐程度与未来贷款拖欠的可能性呈负相关。相反,这种不当行为出现的可能性随着恐惧表达的程度而增加。这些结果与来自现有的心理学和经济学文献的借款人未来收入的充分性和不确定性有关的两个经济渠道一致。我们的研究为市场贷款人和政策制定者提供了重要的实际意义。