using neural network to determine input excesses, output shortfalls and efficiency of dmus in russell model

Data envelopment analysis (dea) has two fundamental approaches for assessing the efficiency with different characteristics; radial and non-radial models. this paper is concerned the non-radial model of russell which is a non linear model. conventional dea for a large dataset with many inputs/outputs would require huge computer resources in terms of memory and cpu time. artificial neural network (ann) is one of the most popular techniques for non linear models and for measuring the relative efficiency of a large dataset with many inputs/ outputs. also in the last decade researches focused on efficiency evaluation via dea as well as using ann. in this paper we will estimate the input excesses and the output shortfalls in addition to efficiency of decision making units (dmus) in russell model through ann. the proposed integrated approach is applied to an actual iranian bank set; the result indicates that it yields a satisfactory solution works.