SpEeakferfs icieConmmcittyee evPaublliucatiaonts ionRe goistfra tiofnuzzInyfo rmtawtiono-sItmapogrtaent ddatees cisWioorksnhop-s Special Session making units with undesirable variables based on the expected value

Data Envelopment Analysis (DEA) is a nonparametric approach for the efficiency evaluation and comparison of decision-making units (DMUs). Although there have been a multitude of studies on single-stage DEA models with undesirable input-outputs, twostage DEA with undesirable variables is still an under-researched subject. Considering the importance of efficiency evaluation of fuzzy two-stage DMUs, this paper presents aFuzzy Two-Stage Data Envelopment Analysis (FTSDEA) model based on the expected value and the credibility theory. Given the use of expected value concept in the objective function and constraints of the proposed model, the FTSDEA model is transformed into its deterministic program equivalent based on the assumption that all data are independent triangular fuzzy numbers. The resulting deterministic programming model isthen used to determine the efficiency of fuzzy two-stage DMUs with undesirable variables. In the end, the performance of the proposed model is illustrated with an example

Keywords:

DEA , Two-Stage , Fuzzy , Credibility Measure , Expected Value , Undesirable