A New Clustering Technic by the Preferences of the Objective in Data Envelopment Analysis

The ways of placing decision making units (DMUs) in certain clusters are found as a subject in statistics, these ways usually are heuristic. The proposed clustering approach in this article considers preferences of DMUs. This study applies Data Envelopment Analysis (DEA); DMUs are clustered by solving multi-objective linear problem (MOLP) and by considering preferences of each DMU at production of each output or consumption of each input. All of DMUs are partitioned into k clusters based on their reference units. The models can be classic models in DEA; in the article clustering DMUs are in the base of CCR envelopment model in which reference units play an important role. The idea of axial solutions is used for solving MOLPs that considers preferences of DMUs. As result, clustering DMUs is done by optimization solutions that are most preference solution at point of view of the decision maker. Moreover, a numerical example is presented and the approach is compared with two other different methods.