A hybrid machine learning framework for analyzing human decision-making through learning preferences * , **
Guo, Mengzhuo1,2; Zhang, Qingpeng2; Liao, Xiuwu1; Chen, Frank Youhua3; Zeng, Daniel Dajun4
刊名OMEGA-INTERNATIONAL JOURNAL OF MANAGEMENT SCIENCE
2021-06-01
卷号101页码:18
关键词Decision analysis Business analytics Predictive modeling Big data analytics Machine learning Multiple criteria decision analysis
ISSN号0305-0483
DOI10.1016/j.omega.2020.102263
通讯作者Zhang, Qingpeng(qingpeng.zhang@cityu.edu.hk)
英文摘要Multiple criteria decision aiding (MCDA) is a family of analytic approaches to depicting the rationale of human decisions. To better interpret the contributions of individual attributes to the decision maker, the conventional MCDA approaches assume that the attributes are monotonic and preference independence. However, the capacity in describing the decision maker & rsquo;s preferences is sacrificed as a result of model simplification. To meet the decision maker & rsquo;s demand for more accurate and interpretable decision models, we propose a novel hybrid method, namely Neural Network-based Multiple Criteria Decision Aiding (NN-MCDA), which combines MCDA model and machine learning to achieve better prediction performance while capturing the relationships between individual attributes and the prediction. NN-MCDA uses a linear component (in an additive form of a set of polynomial functions) to characterize such relationships through providing explicit non-monotonic marginal value functions, and a nonlinear component (in a standard multilayer perceptron form) to capture the implicit high-order interactions among attributes and their complex nonlinear transformations. We demonstrate the effectiveness of NN-MCDA with extensive simulation studies and three real-world datasets. The study sheds light on how to improve the prediction performance of MCDA models using machine learning techniques, and how to enhance the interpretability of machine learning models using MCDA approaches. (c) 2020 Elsevier Ltd. All rights reserved.
资助项目National Natural Science Foundation of China[71972164] ; National Natural Science Foundation of China[71672163] ; National Natural Science Foundation of China[71872144] ; National Natural Science Foundation of China[91846110] ; National Natural Science Foundation of China[71621002] ; Health and Medical Research Fund[16171991] ; Chinese Academy of Sciences[ZDRW-XH-2017-3] ; Ministry of Science and Technology of the People's Republic of China[2016QY02D0305]
WOS研究方向Business & Economics ; Operations Research & Management Science
语种英语
出版者PERGAMON-ELSEVIER SCIENCE LTD
WOS记录号WOS:000626604000010
资助机构National Natural Science Foundation of China ; Health and Medical Research Fund ; Chinese Academy of Sciences ; Ministry of Science and Technology of the People's Republic of China
内容类型期刊论文
源URL[http://ir.ia.ac.cn/handle/173211/44045]  
专题自动化研究所_复杂系统管理与控制国家重点实验室_互联网大数据与安全信息学研究中心
通讯作者Zhang, Qingpeng
作者单位1.Xi An Jiao Tong Univ, Sch Management, Key Lab Minist Educ Proc Control & Efficiency Eng, Xian 710049, Peoples R China
2.City Univ Hong Kong, Sch Data Sci, Hong Kong 999077, Peoples R China
3.City Univ Hong Kong, Coll Business, Dept Management Sci, Hong Kong 999077, Peoples R China
4.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100049, Peoples R China
推荐引用方式
GB/T 7714
Guo, Mengzhuo,Zhang, Qingpeng,Liao, Xiuwu,et al. A hybrid machine learning framework for analyzing human decision-making through learning preferences * , **[J]. OMEGA-INTERNATIONAL JOURNAL OF MANAGEMENT SCIENCE,2021,101:18.
APA Guo, Mengzhuo,Zhang, Qingpeng,Liao, Xiuwu,Chen, Frank Youhua,&Zeng, Daniel Dajun.(2021).A hybrid machine learning framework for analyzing human decision-making through learning preferences * , **.OMEGA-INTERNATIONAL JOURNAL OF MANAGEMENT SCIENCE,101,18.
MLA Guo, Mengzhuo,et al."A hybrid machine learning framework for analyzing human decision-making through learning preferences * , **".OMEGA-INTERNATIONAL JOURNAL OF MANAGEMENT SCIENCE 101(2021):18.
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。


©版权所有 ©2017 CSpace - Powered by CSpace