LATENT SIMILARITY-ENHANCED CREDIT RISK PREDICTION

• 成果类型: Article
• 署名作者: Zhang, Hongzhe; Qian, Wei; Fang, Xiao
• 署名单位: The Chinese University of Hong Kong, Shenzhen; University of Delaware; University of Delaware
• 刊物名称: MIS QUARTERLY
• ISSN/ISSBN: 0276-7783
• DOI: 10.25300/MISQ/2025/18080
• 发表日期: 2026-06
• 页码: 731-766
• 关键词: Credit risk prediction; latent similarity; Machine Learning; information systems; enabling technologies; ART CLASSIFICATION ALGORITHMS; consumer-credit; CLASSIFIERS; strategies; TUTORIAL; models

摘要

Given the sheer size of the consumer credit market and the huge number of consumer credit users, credit risk prediction, or predicting the probability of consumer credit delinquency (or default), has become a critical problem in the consumer credit industry. Effective credit risk prediction aids financial institutions in granting and managing extensions of credit and can help secure the availability of credit for worthy applicants. While it is desirable to employ both users' intrinsic characteristics and similarities among them for effective credit risk prediction, existing studies rely solely on similarities derived from their observed characteristics and fail to account for unobserved similarities among them. To address this challenge, we propose a latent similarity-enhanced credit risk prediction model, which operationalizes the similarity between a pair of users as a combination of the observed and latent similarities between them. We then present a new design for a new method that estimates the model parameters, learns latent similarities among users, and integrates both observed and latent similarities among users with their intrinsic characteristics for credit risk prediction. We further extend our method to the multiclass and numerical credit risk prediction problems. Extensive empirical evaluations with real-world data demonstrate the superior predictive power of our method over benchmark methods for a broad spectrum of credit risk prediction problems. We also show substantial economic value generated from the superiority of our method through a case study.