The robust maximum expert consensus model with risk aversion

Abstract

The maximum expert consensus model (MECM) is an effective model for achieving consensus during the consensus reaching process (CRP) in group decision making (GDM). However, previous literature on MECM has focused only on the resources in CRP and ignored the uncertainty and the risks resulting from the unpredictable decision environment. To address these issues, this paper constructs novel MECMs that can handle both the uncertainty and risks emerging in the CRP. First, the risk maximum expert consensus model (RMECM) is proposed based on the mean-variance (MV) theory. Then, the novel robust risk maximum expert consensus model (R-RMECM) is developed to address the uncertainty caused by the estimation error of the mean and covariance matrix of unit adjustment cost. Additionally, the R-RMECMs are developed under three uncertain scenarios to comprehensively make the models closer to the real decision environment. Finally, the proposed models are verified by applying them to a specific example of the new energy vehicle subsidy policy negotiation and the sensitivity analysis is also conducted.