A Confidence-based Consensus Model for Multi-Attribute Group Decision Making: Exploring the Bounded Trust Propagation and Personalized Adjustment Willingness

Social trust network (STN) and minimum cost consensus (MCC) models have been widely used to address consensus issues in multi-attribute group decision-making (MAGDM) problems with limited resources. However, most researchers have overlooked the decision maker '(DMs)' confidence levels (CLs) and adjustment willingness implicit in their evaluations. To address these problems, this paper explores a confidence-based MCC model that considers DMs' adjustment willingness in the STN. The proposed model includes several modifications to the traditional trust propagation and consensus optimization models. Firstly, the improved method for measuring CLs of DMs and the confidence-based normalization approach are defined, respectively. Secondly, the bounded trust propagation operator is proposed, which considers the credibility of mediators to complete the STN. Thirdly, the identification rules based on the consensus index and CL are defined, and the MCC model with personalized cost functions and acceptable adjustment thresholds is built to automatically generate adjustment values for non-consensus DMs. Finally, a model to identify the non-cooperative behavior at the element level is established and the hybrid MCC model with persuasion strategies is provided. Finally, a case study is processed to verify the applicability of the proposed model, and comparison and sensitivity analysis are conducted to highlight its benefits.