Stepwise Benchmarking Path Selection in DEA

In order to identify the best performers for the benchmarking process, Data Envelopment Analysis (DEA), a methodology for measuring the relative efficiencies among homogeneous Decision-Making Units (DMUs) and for yielding a reference target for and inefficient DMU along with the corresponding efficiency gap, has been used. The general use of DEA has certain limitations that it might not be feasible for an inefficient DMU to achieve its benchmarking target in a single step. In order to overcome these problems, stepwise benchmarking target selection method has been undertaken. However, it did not consider benchmarking target selecting in optimal aspects. Thus, we propose an optimal benchmarking target selection method that inefficient DMU can select benchmarking target considering multiple benchmarking objectives using DEA. For the benchmarking objectives, the improvement feasibility and the efficiency gap are considered.