通过具有课程学习功能的模态保全图神经网络进行金融违约预测

Daixin Wang, Zhiqiang Zhang, Yeyu Zhao, Kai Huang, Yulin Kang, Jun Zhou
{"title":"通过具有课程学习功能的模态保全图神经网络进行金融违约预测","authors":"Daixin Wang, Zhiqiang Zhang, Yeyu Zhao, Kai Huang, Yulin Kang, Jun Zhou","doi":"arxiv-2403.06482","DOIUrl":null,"url":null,"abstract":"User financial default prediction plays a critical role in credit risk\nforecasting and management. It aims at predicting the probability that the user\nwill fail to make the repayments in the future. Previous methods mainly extract\na set of user individual features regarding his own profiles and behaviors and\nbuild a binary-classification model to make default predictions. However, these\nmethods cannot get satisfied results, especially for users with limited\ninformation. Although recent efforts suggest that default prediction can be\nimproved by social relations, they fail to capture the higher-order topology\nstructure at the level of small subgraph patterns. In this paper, we fill in\nthis gap by proposing a motif-preserving Graph Neural Network with curriculum\nlearning (MotifGNN) to jointly learn the lower-order structures from the\noriginal graph and higherorder structures from multi-view motif-based graphs\nfor financial default prediction. Specifically, to solve the problem of weak\nconnectivity in motif-based graphs, we design the motif-based gating mechanism.\nIt utilizes the information learned from the original graph with good\nconnectivity to strengthen the learning of the higher-order structure. And\nconsidering that the motif patterns of different samples are highly unbalanced,\nwe propose a curriculum learning mechanism on the whole learning process to\nmore focus on the samples with uncommon motif distributions. Extensive\nexperiments on one public dataset and two industrial datasets all demonstrate\nthe effectiveness of our proposed method.","PeriodicalId":501128,"journal":{"name":"arXiv - QuantFin - Risk Management","volume":"68-69 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Financial Default Prediction via Motif-preserving Graph Neural Network with Curriculum Learning\",\"authors\":\"Daixin Wang, Zhiqiang Zhang, Yeyu Zhao, Kai Huang, Yulin Kang, Jun Zhou\",\"doi\":\"arxiv-2403.06482\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"User financial default prediction plays a critical role in credit risk\\nforecasting and management. It aims at predicting the probability that the user\\nwill fail to make the repayments in the future. Previous methods mainly extract\\na set of user individual features regarding his own profiles and behaviors and\\nbuild a binary-classification model to make default predictions. However, these\\nmethods cannot get satisfied results, especially for users with limited\\ninformation. Although recent efforts suggest that default prediction can be\\nimproved by social relations, they fail to capture the higher-order topology\\nstructure at the level of small subgraph patterns. In this paper, we fill in\\nthis gap by proposing a motif-preserving Graph Neural Network with curriculum\\nlearning (MotifGNN) to jointly learn the lower-order structures from the\\noriginal graph and higherorder structures from multi-view motif-based graphs\\nfor financial default prediction. Specifically, to solve the problem of weak\\nconnectivity in motif-based graphs, we design the motif-based gating mechanism.\\nIt utilizes the information learned from the original graph with good\\nconnectivity to strengthen the learning of the higher-order structure. And\\nconsidering that the motif patterns of different samples are highly unbalanced,\\nwe propose a curriculum learning mechanism on the whole learning process to\\nmore focus on the samples with uncommon motif distributions. Extensive\\nexperiments on one public dataset and two industrial datasets all demonstrate\\nthe effectiveness of our proposed method.\",\"PeriodicalId\":501128,\"journal\":{\"name\":\"arXiv - QuantFin - Risk Management\",\"volume\":\"68-69 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-03-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - QuantFin - Risk Management\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2403.06482\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - QuantFin - Risk Management","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2403.06482","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

用户财务违约预测在信贷风险预测和管理中起着至关重要的作用。其目的是预测用户未来无法还款的概率。以往的方法主要是提取用户的个人特征和行为特征,建立二元分类模型来进行违约预测。然而,这些方法并不能获得令人满意的结果,尤其是对于信息有限的用户。尽管最近的研究表明,违约预测可以通过社会关系得到改善,但这些研究未能捕捉到小子图模式层面的高阶拓扑结构。本文提出了一种具有课程学习功能的图案保护图神经网络(MotifGNN),以联合学习原始图中的低阶结构和基于图案的多视图中的高阶结构,从而填补这一空白,用于金融违约预测。具体来说,为了解决基于图案的图中的弱连接性问题,我们设计了基于图案的门控机制,利用从具有良好连接性的原始图中学习到的信息来加强对高阶结构的学习。考虑到不同样本的图案模式极不平衡,我们在整个学习过程中提出了一种课程学习机制,更加关注图案分布不常见的样本。在一个公共数据集和两个工业数据集上的广泛实验证明了我们提出的方法的有效性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Financial Default Prediction via Motif-preserving Graph Neural Network with Curriculum Learning
User financial default prediction plays a critical role in credit risk forecasting and management. It aims at predicting the probability that the user will fail to make the repayments in the future. Previous methods mainly extract a set of user individual features regarding his own profiles and behaviors and build a binary-classification model to make default predictions. However, these methods cannot get satisfied results, especially for users with limited information. Although recent efforts suggest that default prediction can be improved by social relations, they fail to capture the higher-order topology structure at the level of small subgraph patterns. In this paper, we fill in this gap by proposing a motif-preserving Graph Neural Network with curriculum learning (MotifGNN) to jointly learn the lower-order structures from the original graph and higherorder structures from multi-view motif-based graphs for financial default prediction. Specifically, to solve the problem of weak connectivity in motif-based graphs, we design the motif-based gating mechanism. It utilizes the information learned from the original graph with good connectivity to strengthen the learning of the higher-order structure. And considering that the motif patterns of different samples are highly unbalanced, we propose a curriculum learning mechanism on the whole learning process to more focus on the samples with uncommon motif distributions. Extensive experiments on one public dataset and two industrial datasets all demonstrate the effectiveness of our proposed method.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
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