A ranking method based on DEA and PROMETHEE II (a rank based on DEA & PR.II)

In this paper we present an integrated Data Envelopment Analysis-Multiple Criteria Decision Aid (DEA-MCDA) model which can be applied to increase the discrimination power of DEA. The aim is to restrict weight values of a DEA model by using tools from MCDA. This model leads to more reasonable inputs/outputs weights while in classic DEA models, some inputs/outputs may be characterized by very low or high weight values. To achieve this goal we use the stability intervals based on PROMETHEE II (Preference Ranking Organization METHod for Enrichment of Evaluations) as weight constraints in DEA. Furthermore, the unicriterion net flow scores matrix is used instead of the initial evaluation matrix. By doing so, we already integrate preferential information in the DEA process. By construction, the best results are compatible with the PROMETHEE II ranking. Additional comparisons with the outputs of other decision making techniques are provided based on two examples.