可解释人工智能的众多夏普利值:敏感性分析视角

IF 6 2区 管理学 Q1 OPERATIONS RESEARCH & MANAGEMENT SCIENCE
Emanuele Borgonovo , Elmar Plischke , Giovanni Rabitti
{"title":"可解释人工智能的众多夏普利值:敏感性分析视角","authors":"Emanuele Borgonovo ,&nbsp;Elmar Plischke ,&nbsp;Giovanni Rabitti","doi":"10.1016/j.ejor.2024.06.023","DOIUrl":null,"url":null,"abstract":"<div><p>Predictive models are increasingly used for managerial and operational decision-making. The use of complex machine learning algorithms, the growth in computing power, and the increase in data acquisitions have amplified the black-box effects in data science. Consequently, a growing body of literature is investigating methods for interpretability and explainability. We focus on methods based on Shapley values, which are gaining attention as measures of feature importance for explaining black-box predictions. Our analysis follows a hierarchy of value functions, and proves several theoretical properties that connect the indices at the alternative levels. We bridge the notions of totally monotone games and Shapley values, and introduce new interaction indices based on the Shapley-Owen values. The hierarchy evidences synergies that emerge when combining Shapley effects computed at different levels. We then propose a novel sensitivity analysis setting that combines the benefits of both local and global Shapley explanations, which we refer to as the “glocal” approach. We illustrate our integrated approach and discuss the managerial insights it provides in the context of a data-science problem related to health insurance policy-making.</p></div>","PeriodicalId":55161,"journal":{"name":"European Journal of Operational Research","volume":null,"pages":null},"PeriodicalIF":6.0000,"publicationDate":"2024-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0377221724004715/pdfft?md5=9e0452d284fdc06e6ffd43cf5cd218d1&pid=1-s2.0-S0377221724004715-main.pdf","citationCount":"0","resultStr":"{\"title\":\"The many Shapley values for explainable artificial intelligence: A sensitivity analysis perspective\",\"authors\":\"Emanuele Borgonovo ,&nbsp;Elmar Plischke ,&nbsp;Giovanni Rabitti\",\"doi\":\"10.1016/j.ejor.2024.06.023\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Predictive models are increasingly used for managerial and operational decision-making. The use of complex machine learning algorithms, the growth in computing power, and the increase in data acquisitions have amplified the black-box effects in data science. Consequently, a growing body of literature is investigating methods for interpretability and explainability. We focus on methods based on Shapley values, which are gaining attention as measures of feature importance for explaining black-box predictions. Our analysis follows a hierarchy of value functions, and proves several theoretical properties that connect the indices at the alternative levels. We bridge the notions of totally monotone games and Shapley values, and introduce new interaction indices based on the Shapley-Owen values. The hierarchy evidences synergies that emerge when combining Shapley effects computed at different levels. We then propose a novel sensitivity analysis setting that combines the benefits of both local and global Shapley explanations, which we refer to as the “glocal” approach. We illustrate our integrated approach and discuss the managerial insights it provides in the context of a data-science problem related to health insurance policy-making.</p></div>\",\"PeriodicalId\":55161,\"journal\":{\"name\":\"European Journal of Operational Research\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":6.0000,\"publicationDate\":\"2024-06-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S0377221724004715/pdfft?md5=9e0452d284fdc06e6ffd43cf5cd218d1&pid=1-s2.0-S0377221724004715-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"European Journal of Operational Research\",\"FirstCategoryId\":\"91\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0377221724004715\",\"RegionNum\":2,\"RegionCategory\":\"管理学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"OPERATIONS RESEARCH & MANAGEMENT SCIENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"European Journal of Operational Research","FirstCategoryId":"91","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0377221724004715","RegionNum":2,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"OPERATIONS RESEARCH & MANAGEMENT SCIENCE","Score":null,"Total":0}
引用次数: 0

摘要

预测模型越来越多地用于管理和运营决策。复杂机器学习算法的使用、计算能力的提高以及数据获取量的增加,扩大了数据科学中的黑箱效应。因此,越来越多的文献正在研究可解释性和可说明性的方法。我们的重点是基于夏普利值的方法,这种方法作为解释黑箱预测的特征重要性度量,正日益受到关注。我们的分析遵循价值函数的层次结构,并证明了连接不同层次指数的几个理论属性。我们将完全单调博弈和夏普利值的概念联系起来,并基于夏普利-欧文值引入了新的交互指数。层次结构证明了将不同层次计算出的夏普利效应结合在一起所产生的协同效应。然后,我们提出了一种新颖的敏感性分析设置,它结合了局部和全局夏普利解释的优势,我们称之为 "全局 "方法。我们以一个与医疗保险政策制定相关的数据科学问题为背景,说明了我们的综合方法,并讨论了它所提供的管理见解。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
The many Shapley values for explainable artificial intelligence: A sensitivity analysis perspective

Predictive models are increasingly used for managerial and operational decision-making. The use of complex machine learning algorithms, the growth in computing power, and the increase in data acquisitions have amplified the black-box effects in data science. Consequently, a growing body of literature is investigating methods for interpretability and explainability. We focus on methods based on Shapley values, which are gaining attention as measures of feature importance for explaining black-box predictions. Our analysis follows a hierarchy of value functions, and proves several theoretical properties that connect the indices at the alternative levels. We bridge the notions of totally monotone games and Shapley values, and introduce new interaction indices based on the Shapley-Owen values. The hierarchy evidences synergies that emerge when combining Shapley effects computed at different levels. We then propose a novel sensitivity analysis setting that combines the benefits of both local and global Shapley explanations, which we refer to as the “glocal” approach. We illustrate our integrated approach and discuss the managerial insights it provides in the context of a data-science problem related to health insurance policy-making.

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
European Journal of Operational Research
European Journal of Operational Research 管理科学-运筹学与管理科学
CiteScore
11.90
自引率
9.40%
发文量
786
审稿时长
8.2 months
期刊介绍: The European Journal of Operational Research (EJOR) publishes high quality, original papers that contribute to the methodology of operational research (OR) and to the practice of decision making.
×
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