A multi-level sparse attentive fusion network integrating hard and soft information for firm-level loan default prediction

IF 5.9 3区 管理学 Q1 BUSINESS
Jingling Ma , Junqiao Gong , Gang Wang , Xuan Zhang
{"title":"A multi-level sparse attentive fusion network integrating hard and soft information for firm-level loan default prediction","authors":"Jingling Ma ,&nbsp;Junqiao Gong ,&nbsp;Gang Wang ,&nbsp;Xuan Zhang","doi":"10.1016/j.elerap.2025.101479","DOIUrl":null,"url":null,"abstract":"<div><div>Firm-level loan default prediction (FLDP) deserves much attention from both academic and industry. Even a small improvement in the accuracy of FLDP could lead to significant savings by reducing credit risk. While previous studies have utilized deep learning models for FLDP task, they failed to well handle the intra-type ambiguity and inter-type interaction simultaneously facing with combined hard and soft information, thus remaining an area of ongoing development. By this perspective, we seek to design a novel Multi-level Sparse Attention (MLSA) based deep learning fusion framework for FLDP, aiming to fully capture default signals conveyed from both hard and soft information. First, multiple types of information are extracted grounded in 5P theory and LAPP theory, ensuring the sufficiency and rationality of the features. Second, Sparse Attentive MLP (SA-MLP) and Sparse Attentive GRU (SA-GRU) module are proposed to handle the intra-type ambiguity embedded in hard and soft information separately. Further, the Attentive Fusion (AF) module including Differential Enhancive module and Common Selective module is proposed to explore inter-type interaction among hard and soft information. Last, we adopt the focal loss function to mitigate the adverse effects of imbalanced data. The proposed MLSA informs future FLDP research about how to fully exploit the value of hard and soft information by considering their intra-type ambiguity and inter-type interaction. Empirical evaluation of the MLSA on a real-world dataset demonstrates its outperformance of state-of-the-art benchmarks in the FLDP task. Our results also contribute to the growing literature on this topic by highlighting the roles of hard and soft information and improving interpretability.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"70 ","pages":"Article 101479"},"PeriodicalIF":5.9000,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Electronic Commerce Research and Applications","FirstCategoryId":"91","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1567422325000043","RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"BUSINESS","Score":null,"Total":0}
引用次数: 0

Abstract

Firm-level loan default prediction (FLDP) deserves much attention from both academic and industry. Even a small improvement in the accuracy of FLDP could lead to significant savings by reducing credit risk. While previous studies have utilized deep learning models for FLDP task, they failed to well handle the intra-type ambiguity and inter-type interaction simultaneously facing with combined hard and soft information, thus remaining an area of ongoing development. By this perspective, we seek to design a novel Multi-level Sparse Attention (MLSA) based deep learning fusion framework for FLDP, aiming to fully capture default signals conveyed from both hard and soft information. First, multiple types of information are extracted grounded in 5P theory and LAPP theory, ensuring the sufficiency and rationality of the features. Second, Sparse Attentive MLP (SA-MLP) and Sparse Attentive GRU (SA-GRU) module are proposed to handle the intra-type ambiguity embedded in hard and soft information separately. Further, the Attentive Fusion (AF) module including Differential Enhancive module and Common Selective module is proposed to explore inter-type interaction among hard and soft information. Last, we adopt the focal loss function to mitigate the adverse effects of imbalanced data. The proposed MLSA informs future FLDP research about how to fully exploit the value of hard and soft information by considering their intra-type ambiguity and inter-type interaction. Empirical evaluation of the MLSA on a real-world dataset demonstrates its outperformance of state-of-the-art benchmarks in the FLDP task. Our results also contribute to the growing literature on this topic by highlighting the roles of hard and soft information and improving interpretability.
求助全文
约1分钟内获得全文 求助全文
来源期刊
Electronic Commerce Research and Applications
Electronic Commerce Research and Applications 工程技术-计算机:跨学科应用
CiteScore
10.10
自引率
8.30%
发文量
97
审稿时长
63 days
期刊介绍: Electronic Commerce Research and Applications aims to create and disseminate enduring knowledge for the fast-changing e-commerce environment. A major dilemma in e-commerce research is how to achieve a balance between the currency and the life span of knowledge. Electronic Commerce Research and Applications will contribute to the establishment of a research community to create the knowledge, technology, theory, and applications for the development of electronic commerce. This is targeted at the intersection of technological potential and business aims.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信