Evaluation the efficiency in the presence of adaptable measure and in fuzzy environment

In conventional data envelopment analysis (DEA) models, the efficiencies of decision making units (DMUs) with precise data are usually evaluated from optimistic point of view in which the status of each variable (i.e. input/output) is certain. Nevertheless, there are situations in the real world that measures can play both input and output roles in a fuzzy environment. In this study, measures with two roles, input and output, are defined as adaptable variables. This paper proposes a method for estimating the performance of DMUs where adaptable and fuzzy data exist. Indeed, efficiencies are calculated from two aspects, optimistic and pessimistic, when adaptable and fuzzy data present. Two different efficiencies are integrated into a geometric average efficiency. Therefore, the overall efficiency is calculated and adaptable variables are split into input and output variables in evaluating the efficiency of each DMU. A numerical example is applied to clarifying the approach