a novel inverse dea approach based on the general production possibility set for negative data

Traditional inverse data envelopment analysis (inverse dea) models assume that the inputs and outputs of the decision making units (dmus) are non-negative. in this paper, we first present the inverse dea models to determine the optimal level of inputs and outputs in the case that some of the input and output components of the observed dmus are negative. these levels are determined based on the target efficiency score of the dmu under evaluation. for this purpose, we present three different models in variable returns to technology to determine optimal levels. to solve each model, we determine the counterpart dmu corresponding to the unit under evaluation. this unit is determined based on the additive model, and then we get the level of the target and the observed outputs corresponding to the dmu under evaluation to determine which of these three models to use to measure the efficiency of the dmu under evaluation. we describe the presented approach with a numerical example and use it to measure the optimal levels of inputs and outputs of bank branches. at the end, we bring the results.