A Multi-Attribute Group Decision-Making Method Based on Trust Relationship and DEA Regret Cross-Efficiency
提出一种结合信任关系和DEA遗憾交叉效率的多属性群决策方法，通过引入决策者的风险心理和专家信任权重，改进传统DEA交叉效率的完全理性假设，并用数值例子验证了方法的优越性和合理性。
In multiattribute group decision-making (MAGDM) problems, the data envelopment analysis (DEA) cross-efficiency method is an effective tool to evaluate each decision-making unit. However, this method usually assumes that the decision-maker (DM) is completely rational, which ignores the risk psychology of the DM in the decision-making process. To compensate for this deficiency, this article proposes an MAGDM method based on trust relationships and DEA regret cross-efficiency. First, we construct a modified model based on the CCR model. Then, we propose the DEA regret cross-efficiency method. This method involves the risk psychology of the DM in the decision-making process. Next, a weighting model is developed to aggregate the cross-efficiency comprehensive utility matrix. Subsequently, we construct trust propagation and trust aggregation models to obtain the weights of experts. Finally, the MAGDM method based on trust relationships and DEA regret cross-efficiency is designed to rank all alternatives. A numerical example is provided to illustrate the superiority and rationality of our proposed method.