Two-stage DEA Model And Its Application On Efficiency Of Commercial Bank

Data envelopment analysis (DEA) is a non-parametric technique for measuring and evaluating the relative efficiencies of decision making units (DMUs) with more than one input and output. With the unique characteristic and superiority, it becomes the focus of study. It has got rapid development in theories and applications, and now it has become the common and important analysis tool and research method in management science, system engineering, decision analysis, evaluating technique and other fields. Two-stage DEA is a new research field with very wide applications.Firstly, this paper briefly reviews the historical development of DEA method, introduces the basic concepts of DEA model and the DEA applied fields, and summarizes the general steps of this method.Secondly, for two-stage production containing some intermediate measures, a new two-stage nonlinear DEA model is established through the properties of multi-objective programming. The model's properties are discussed such as its equivalence model( Z 2R -model), existence of the solution and the efficiency of the Decision Making Unites(DMUs) for Z 2R -model. Furthermore, Z 2R-model is converted to the model containing only one nonlinear item, which could be treated as a linear model including a parameter. Especially, it is proven that if there is only one intermediate measure, the two-stage nonlinear DEA model can be converted to a linear model, which also equivalent to two independent single stage DEA models.Thirdly, the two-stage DEA model is used to analyze the efficiency of commercial bank in which deposit is a intermediate measure. We establish the equivalence of weak efficient solution between our model( Z 2R-model), Chen-Zhu model and C 2 R (1), C 2 R (2) model. In this paper, we list and compare the different solutions of four models.Finally, this paper summary the conclusions of above analysis and point out some considerations for future research.