An endo-confidence-based consensus with hierarchical clustering and automatic feedback in multi-attribute large-scale group decision-making

With the development of novel technological and societal paradigms, consensus in multi-attribute large-scale group decision making is of great significance. The confidence derived by evaluation is considered in this paper and it is named as endo-confidence. Then, a novel adaptive consensus model to manage endo-confident behavior is proposed. First, the experts are classified by their evaluations as the first cluster, and then by their endo-confidence levels in each cluster named as sub-cluster. Furthermore, the new method considering endo-confidence level is introduced to determine the weights. To better manage consensus reaching process, we further discuss three types of experts in the non-consensus cluster to adjust their evaluations, including i) experts who are lack of endo-confidence, ii) experts who are over endo-confidence, and iii) experts whose evaluations greatly deviate from the overall level. Next, an automatic feedback mechanism which considers both evaluations and endo-confidence levels of experts is proposed for the non-consensus experts. Finally, a case study is carried out to demonstrate the feasibility of the proposed model, and a series of comparative analyses are used to show its stability.