报告人：李武

报告人单位：加拿大温莎大学

报告时间：2023年9月26日（周二）下午14:00

报告地点：笃行楼102

举办单位:数理科学学院

报告人简介：

李武(Kevin W. Li)博士,加拿大温莎大学Odette商学院管理科学教授。主要研究方向包括供应链管理、决策理论与方法以及冲突分析等。研究获得三项加拿大自然科学与工程研究基金会发现基金项目的支持，同时也多次得到国家教育部春晖计划短期项目支持以及日本学术振兴会（JSPS）外籍聘用研究员（Invitational Fellowship）项目的支持于2011年和2015年到东京工业大学进行访问研究。自2001年以来，在国际期刊如Production and Operations Management,European Journal of Operational Research, IEEE Transactions on Systems, Man, and Cybernetics: Part A, Information Sciences, International Journal of Production Economics, International Journal of Production Research, Transportation Research: Part E, WaterResources Research等发表69篇学术论文，李武教授的研究工作得到国内外同行的广泛引用(SCI/SSCI累计引用2656次，h指数30)，五篇论文先后列为ESI高被引论文，在相关领域产生了一定影响，现任《Group Decision and Negotiation》及多个国际期刊的Associate Editor或编委。

报告摘要：

Thebenefitofthedoubt (BoD)isa non-parametric weighting method that aimsto maximize the relativecomposite indicatorvalue of eachdecision-making unit (DMU).A well-known issue ofBoD-basedranking of DMUsisthe rank reversal problem whenDMUsaredeletedor added. Thefundamentalreasonfor rank reversalsis that deleting(or adding)aDMU influencesthe generatedweight bychangingthe frontier surface. To address the rank reversal problem, this paper proposes asubgroupdominance-basedBoD model (SD-BoD). Based on the individualweights obtained fromaclassicBoDmodel,adominance-based pairwise comparison mechanismisput forwardtoensurecomparability of different DMUs. Moreover, motivated by thedataenvelopmentanalysisidea, we construct a sequentialfrontier surfacepartition technique and establish a DMUrankingframework based on subgroupdominance, which helps reduce weightvariationdue toDMUaddition or deletion. Finally,the effectiveness of the SD-BoD method is illustrated by comparing andanalyzing theHuman Development Indicesofthe28 European regions.

审核：蔡亚峰