A Good Sketch is Better than A Long Speech: Evaluate Delinquency Risk through Real-Time Video Analysis

58 Pages Posted: 13 Dec 2023 Last revised: 13 Nov 2024

See all articles by Xiangyu Chang

Xiangyu Chang

Xi'an Jiaotong University (XJTU) - School of Management

Lili Dai

University of New South Wales (UNSW)

Lingbing Feng

Jiangxi University of Finance and Economics

Jianlei Han

Macquarie University - Faculty of Business and Economics

Jing Shi

Macquarie University

Bohui Zhang

The Chinese University of Hong Kong, Shenzhen

Date Written: December 10, 2023

Abstract

This paper proposes an innovative method to assess borrowers’ creditworthiness in consumer credit markets by conducting 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’ micro facial expressions of happiness is negatively associated with loan delinquency likelihood, while the degree of fear expressions is positively associated with delinquency risk. 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 fintech lenders and policymakers.

Keywords: Loan delinquency risk, Real-time data, Video analysis, Machine learning, Fintech

JEL Classification: D14, G14, G23, G51

Suggested Citation

Chang, Xiangyu and Dai, Lili and Feng, Lingbing and Han, Jianlei and Shi, Jing and Zhang, Bohui, A Good Sketch is Better than A Long Speech: Evaluate Delinquency Risk through Real-Time Video Analysis (December 10, 2023). Available at SSRN: https://ssrn.com/abstract=4659659

Xiangyu Chang

Xi'an Jiaotong University (XJTU) - School of Management ( email )

28,Xianning West Road
Xi'an, Shaanxi 710049
China

Lili Dai (Contact Author)

University of New South Wales (UNSW) ( email )

Kensington
High St
Sydney, NSW 2052
Australia

HOME PAGE: http://sites.google.com/site/ldaiprofile

Lingbing Feng

Jiangxi University of Finance and Economics ( email )

South Lushan Road
Nanchang, Jiangxi 330013
China

Jianlei Han

Macquarie University - Faculty of Business and Economics ( email )

Sydney, New South Wales 2109
Australia

Jing Shi

Macquarie University ( email )

Eastern Rd.
North Ryde
Sydney, NSW 2109
Australia

HOME PAGE: http://https://researchers.mq.edu.au/en/persons/jing-shi

Bohui Zhang

The Chinese University of Hong Kong, Shenzhen ( email )

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
119
Abstract Views
2,204
Rank
483,856
PlumX Metrics