A new DEA model for finding most efficient DMU with imprecise data

Data Envelopment Analysis (DEA) is a widely recognized approach for evaluating the efficiencies of decision making units (DMUs). Because of easy and successful application and case studies, DEA has gained much attention and widespread use by business and academy researchers. The conventional DEA models (e.g. BCC and CCR) make an assumption that input and output data are exact values on a ratio scale. However, in real cases it is not feasible to define and calculate an exact value for some inputs and outputs. Recently, researchers addressed the problem of imprecise data in DEA, in its general form. The term ‘‘imprecise data’’ reflects the situation where some of the input and output data are only known to be placed within bounded intervals (interval numbers) while other data are known only up to an order. This paper, proposes a new DEA model which allows user to find most efficient DMU, considering imprecise data (interval and ordinal data). As an advantage, proposed model in efficient and find most efficient DMU by solving one model, while considering imprecise data. Moreover, applicability of proposed model is illustrated in a supplier selection problem. In this case, 18 suppliers with imprecise data were evaluated and most efficient one has been selected. Finally, results of proposed model were compared with a previously published model in literature.