A new simulation-based genetic algorithm to efficiency measure in IDEA with weight restrictions

To efficiency measure in real-life applications of data envelopment analysis (DEA) model, the inputs and outputs data are sometimes imprecise, and we need to use the weight restrictions in order to incorporate management's views. For this purpose, the present paper investigates the problems of existing approaches in this area, and proposes a comprehensive DEA model which enables us to estimate the relative efficiency scores of real-life systems. The proposed model contains different types of imprecise data and general form of weight restrictions. A new simulation-based genetic algorithm (GA) is developed to estimate the expected values of relative efficiencies with the comprehensive DEA model. It is shown that the proposed model and the solution approach solves the drawbacks of existing models, and gives more informative and reliable results. Some numerical examples are provided to illustrate the theoretical content of the paper and to show the effectiveness of the new approach.