利用 ICEnet 实现神经网络的平滑性和单调性约束

IF 1.5 Q3 BUSINESS, FINANCE
Ronald Richman, Mario V. Wüthrich
{"title":"利用 ICEnet 实现神经网络的平滑性和单调性约束","authors":"Ronald Richman, Mario V. Wüthrich","doi":"10.1017/s174849952400006x","DOIUrl":null,"url":null,"abstract":"<p>Deep neural networks have become an important tool for use in actuarial tasks, due to the significant gains in accuracy provided by these techniques compared to traditional methods, but also due to the close connection of these models to the generalized linear models (GLMs) currently used in industry. Although constraining GLM parameters relating to insurance risk factors to be smooth or exhibit monotonicity is trivial, methods to incorporate such constraints into deep neural networks have not yet been developed. This is a barrier for the adoption of neural networks in insurance practice since actuaries often impose these constraints for commercial or statistical reasons. In this work, we present a novel method for enforcing constraints within deep neural network models, and we show how these models can be trained. Moreover, we provide example applications using real-world datasets. We call our proposed method <span>ICEnet</span> to emphasize the close link of our proposal to the individual conditional expectation model interpretability technique.</p>","PeriodicalId":44135,"journal":{"name":"Annals of Actuarial Science","volume":null,"pages":null},"PeriodicalIF":1.5000,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Smoothness and monotonicity constraints for neural networks using ICEnet\",\"authors\":\"Ronald Richman, Mario V. Wüthrich\",\"doi\":\"10.1017/s174849952400006x\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Deep neural networks have become an important tool for use in actuarial tasks, due to the significant gains in accuracy provided by these techniques compared to traditional methods, but also due to the close connection of these models to the generalized linear models (GLMs) currently used in industry. Although constraining GLM parameters relating to insurance risk factors to be smooth or exhibit monotonicity is trivial, methods to incorporate such constraints into deep neural networks have not yet been developed. This is a barrier for the adoption of neural networks in insurance practice since actuaries often impose these constraints for commercial or statistical reasons. In this work, we present a novel method for enforcing constraints within deep neural network models, and we show how these models can be trained. Moreover, we provide example applications using real-world datasets. We call our proposed method <span>ICEnet</span> to emphasize the close link of our proposal to the individual conditional expectation model interpretability technique.</p>\",\"PeriodicalId\":44135,\"journal\":{\"name\":\"Annals of Actuarial Science\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.5000,\"publicationDate\":\"2024-04-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Annals of Actuarial Science\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1017/s174849952400006x\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"BUSINESS, FINANCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Annals of Actuarial Science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1017/s174849952400006x","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"BUSINESS, FINANCE","Score":null,"Total":0}
引用次数: 0

摘要

深度神经网络已成为精算任务中的重要工具,这不仅是因为与传统方法相比,这些技术显著提高了精确度,还因为这些模型与目前行业中使用的广义线性模型(GLM)密切相关。尽管约束与保险风险因素相关的 GLM 参数使其平滑或表现出单调性并不难,但将此类约束纳入深度神经网络的方法尚未开发出来。这阻碍了神经网络在保险实践中的应用,因为精算师通常会出于商业或统计原因施加这些约束。在这项工作中,我们提出了一种在深度神经网络模型中实施约束的新方法,并展示了如何训练这些模型。此外,我们还提供了使用真实世界数据集的应用实例。我们将所提出的方法称为 ICEnet,以强调我们的建议与单个条件期望模型可解释性技术的密切联系。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Smoothness and monotonicity constraints for neural networks using ICEnet

Deep neural networks have become an important tool for use in actuarial tasks, due to the significant gains in accuracy provided by these techniques compared to traditional methods, but also due to the close connection of these models to the generalized linear models (GLMs) currently used in industry. Although constraining GLM parameters relating to insurance risk factors to be smooth or exhibit monotonicity is trivial, methods to incorporate such constraints into deep neural networks have not yet been developed. This is a barrier for the adoption of neural networks in insurance practice since actuaries often impose these constraints for commercial or statistical reasons. In this work, we present a novel method for enforcing constraints within deep neural network models, and we show how these models can be trained. Moreover, we provide example applications using real-world datasets. We call our proposed method ICEnet to emphasize the close link of our proposal to the individual conditional expectation model interpretability technique.

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
CiteScore
3.10
自引率
5.90%
发文量
22
×
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