Solving interval DEA model and ranking based on interval-oriented and grey incidence degree

The classical algorithm of solving interval DEA models depends much on evaluator's subjective discrimination, and has also some shortages, e.g. the efficiency interval length might be too long to evaluate the effectiveness of decision-making unit well if the range of the input and output variables interval is large. Aimming to the advantages and disadvantages of both methods, an improved method, named interval-oriented method, is presented to solve DEA model with interval data. The result of the new method depends less on evaluator's subjective discrimination, and its length is shorter. Furthermore, a way to rank decision-making units based on the grey incidence degree is given.