Social network-based consensus reaching model with rational adjustment allocation for large-scale group decision making

Abstract

Large-scale group decision making (LSGDM) refers to the decision-making process involving a large number of decision makers (DMs). As an extension of group decision-making, it can make full use of multiple resources and give play to complementary advantages of the knowledge structure of the large group, but it faces some problems such as difficult concentration of opinion, long decision-making time and difficult management. In LSGDM, individual optimality and fairness regarding consensus adjustment are concerns for DMs. Many existing consensus models assume that DMs are completely cooperative and aim only at global optimality such as the minimization of the total consensus cost. It will be difficult for DMs to fully accept the resulting adjustment suggestion. Therefore, an LSGDM method based on the cooperative game is proposed. First, a new method of trust propagation is developed to calculate a more reliable indirect trust degree between unacquainted DMs. Next, an adaptive clustering algorithm is devised to more objectively cluster the large group into several subgroups. Then, consensus adjustment optimization models are built from the global and individual perspectives, respectively. The difference in the adjustment amount derived from the two perspectives is viewed as a cooperative surplus, which is fairly allocated through a core-based maximum entropy model. Based on the allocation scheme, an overall consensus optimization model considering personalized adjustment preferences is built to determine the final opinion adjustments. Finally, a practical example is provided to illustrate the decision-making process. Furthermore, the comparative analysis shows the advantages of the proposed method.