a development on ahp/dea methodology for ranking decision making units

the ahp/dea methodology is an integration of analytical hierarchical process (ahp) and data envelopment analysis. this method uses the capabilities of both ahp and dea. however, it has some problems: it illogically compares two decision-making units in a data envelopment analysis (dea) model, it is not compatible with dea ranking in the case of multiple inputs/multiple outputs, and it leads to weak discrimination in the cases that number of inputs and outputs is large. in this paper, we propose a development on the first stage of the two-stage ahp/dea methodology that removes the mentioned problems. in the first stage, we develop a model which considers the effects of each unit on the others, and the second step is the same of the main method. numerical examples are presented in the paper to illustrate the advantages of the developed ahp/dea methodology