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

•A consensus model based on endo-confidence is constructed.•Double hierarchical clustering is introduced in the consensus reaching process. Firstly, the experts are classified according to their evaluations (the numerical evaluations given by experts) as the first hierarchical cluster, and then according to their endo-confidence levels in each first hierarchical cluster as the subcluster.•Three types of experts who need to adjust their evaluations are defined. Furthermore, an automatic adjustment mechanism considering endo-confidence levels is given.