A Large-Scale Group Decision Making Model Based on Adaptive Subgroup Rescue Mechanism

This paper proposes an adaptive subgroup rescue mechanism to better balance efficiency and information loss in large-scale group decision-making. We calculate the consensus for different clusters through linguistic preferences and trust relations, find the group with the lowest consensus level, and advise the group to exit from the process. A rescue process is triggered once the group has low cohesion or can propose a new idea. A trust-based feedback mechanism is designed to ensure enough decision makers in consensus reaching. Finally, we conduct an empirical study to verify the feasibility of our mechanism.