为美国空军飞行员候选人选拔提供负责任的机器学习

IF 6.7 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Decision Support Systems Pub Date : 2024-02-21 DOI:10.1016/j.dss.2024.114198
Devin Wasilefsky , William N. Caballero , Chancellor Johnstone , Nathan Gaw , Phillip R. Jenkins
{"title":"为美国空军飞行员候选人选拔提供负责任的机器学习","authors":"Devin Wasilefsky ,&nbsp;William N. Caballero ,&nbsp;Chancellor Johnstone ,&nbsp;Nathan Gaw ,&nbsp;Phillip R. Jenkins","doi":"10.1016/j.dss.2024.114198","DOIUrl":null,"url":null,"abstract":"<div><p>The United States Air Force (USAF) continues to be plagued by a chronic pilot shortage, one that could be exacerbated by an accompanying shortfall in the commercial airlines. As a result, efforts have increased to alleviate this shortage by finding methods to reduce pilot training attrition. We contribute to these efforts by setting forth a decision support system (DSS) for pilot candidate selection using modern machine learning techniques. In view of the recent Responsible Artificial Intelligence Strategy published by the United States Department of Defense, this research leverages interpretable and explainable machine learning methods to create traceable and equitable models that may be responsibly and reliably governed. These models are used to regress candidates’ average merit assignment selection system scores based on information available for selection and prior to training. More specifically, using data provided by the USAF from 2010 to 2018, this paper develops and analyzes multiple interpretable models based on Gaussian Bayesian networks, as well as multiple black-box models rendered explainable by SHAP values and conformal prediction. A preferred pair of interpretable and explainable models is selected and embedded within a DSS for USAF pilot candidate selection boards: the Air Force Pilot Applicant Selection System. The utilization of this DSS is explored, the analyses it enables are discussed, and relevant USAF policymaking issues are examined.</p></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"180 ","pages":"Article 114198"},"PeriodicalIF":6.7000,"publicationDate":"2024-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Responsible machine learning for United States Air Force pilot candidate selection\",\"authors\":\"Devin Wasilefsky ,&nbsp;William N. Caballero ,&nbsp;Chancellor Johnstone ,&nbsp;Nathan Gaw ,&nbsp;Phillip R. Jenkins\",\"doi\":\"10.1016/j.dss.2024.114198\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>The United States Air Force (USAF) continues to be plagued by a chronic pilot shortage, one that could be exacerbated by an accompanying shortfall in the commercial airlines. As a result, efforts have increased to alleviate this shortage by finding methods to reduce pilot training attrition. We contribute to these efforts by setting forth a decision support system (DSS) for pilot candidate selection using modern machine learning techniques. In view of the recent Responsible Artificial Intelligence Strategy published by the United States Department of Defense, this research leverages interpretable and explainable machine learning methods to create traceable and equitable models that may be responsibly and reliably governed. These models are used to regress candidates’ average merit assignment selection system scores based on information available for selection and prior to training. More specifically, using data provided by the USAF from 2010 to 2018, this paper develops and analyzes multiple interpretable models based on Gaussian Bayesian networks, as well as multiple black-box models rendered explainable by SHAP values and conformal prediction. A preferred pair of interpretable and explainable models is selected and embedded within a DSS for USAF pilot candidate selection boards: the Air Force Pilot Applicant Selection System. The utilization of this DSS is explored, the analyses it enables are discussed, and relevant USAF policymaking issues are examined.</p></div>\",\"PeriodicalId\":55181,\"journal\":{\"name\":\"Decision Support Systems\",\"volume\":\"180 \",\"pages\":\"Article 114198\"},\"PeriodicalIF\":6.7000,\"publicationDate\":\"2024-02-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Decision Support Systems\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0167923624000319\",\"RegionNum\":1,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Decision Support Systems","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0167923624000319","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

摘要

美国空军(USAF)长期以来一直受到飞行员短缺的困扰,而商业航空公司的飞行员短缺可能会加剧这一问题。因此,通过寻找减少飞行员培训自然减员的方法来缓解这一短缺问题的努力不断增加。我们利用现代机器学习技术,为飞行员候选人的选择建立了一个决策支持系统(DSS),从而为这些努力做出了贡献。鉴于美国国防部最近发布的 "负责任的人工智能战略",这项研究利用可解释和可说明的机器学习方法来创建可追溯和公平的模型,并对其进行负责任和可靠的管理。这些模型用于根据选拔和培训前的可用信息,对候选人的平均择优分配选拔系统得分进行回归。更具体地说,利用美国空军提供的 2010 年至 2018 年的数据,本文开发并分析了基于高斯贝叶斯网络的多个可解释模型,以及由 SHAP 值和符合性预测呈现的多个可解释黑箱模型。本文选择了一对首选的可解释和可解释模型,并将其嵌入美国空军飞行员候选人遴选委员会的 DSS 系统:空军飞行员申请人遴选系统。本文探讨了该 DSS 的使用情况,讨论了它所支持的分析,并研究了美国空军的相关决策问题。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Responsible machine learning for United States Air Force pilot candidate selection

The United States Air Force (USAF) continues to be plagued by a chronic pilot shortage, one that could be exacerbated by an accompanying shortfall in the commercial airlines. As a result, efforts have increased to alleviate this shortage by finding methods to reduce pilot training attrition. We contribute to these efforts by setting forth a decision support system (DSS) for pilot candidate selection using modern machine learning techniques. In view of the recent Responsible Artificial Intelligence Strategy published by the United States Department of Defense, this research leverages interpretable and explainable machine learning methods to create traceable and equitable models that may be responsibly and reliably governed. These models are used to regress candidates’ average merit assignment selection system scores based on information available for selection and prior to training. More specifically, using data provided by the USAF from 2010 to 2018, this paper develops and analyzes multiple interpretable models based on Gaussian Bayesian networks, as well as multiple black-box models rendered explainable by SHAP values and conformal prediction. A preferred pair of interpretable and explainable models is selected and embedded within a DSS for USAF pilot candidate selection boards: the Air Force Pilot Applicant Selection System. The utilization of this DSS is explored, the analyses it enables are discussed, and relevant USAF policymaking issues are examined.

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
Decision Support Systems
Decision Support Systems 工程技术-计算机:人工智能
CiteScore
14.70
自引率
6.70%
发文量
119
审稿时长
13 months
期刊介绍: The common thread of articles published in Decision Support Systems is their relevance to theoretical and technical issues in the support of enhanced decision making. The areas addressed may include foundations, functionality, interfaces, implementation, impacts, and evaluation of decision support systems (DSSs).
期刊最新文献
A comparative analysis of the effect of initiative risk statement versus passive risk disclosure on the financing performance of Kickstarter campaigns DeepSecure: A computational design science approach for interpretable threat hunting in cybersecurity decision making Editorial Board Effects of visual-preview and information-sidedness features on website persuasiveness The evolution of organizations and stakeholders for metaverse ecosystems: Editorial for the special issue on metaverse part 1
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1