An approach based on double-frontier DEA for determining priorities and obtaining weights in AHP

The Analytic Hierarchy Process (AHP) is a multiple criteria decision-making method extensively used in various fields. Prioritization of decision criteria or alternatives from pairwise comparison matrices in AHP has been studied extensively. This article proposed the “Double-Frontier DEA” approach for prioritization in AHP. This new approach uses two optimistic and pessimistic DEA models to obtain the best local priorities from a pairwise comparison matrix, regardless of whether it is fully consistent or not.

One of these methods is Data Envelopment Analysis (DEA). The combination of DEA and AHP (DEAHP) is used to obtain and aggregate weights in AHP. Studies show that DEAHP fails in obtaining and aggregating weights in AHP and sometimes produces priority vectors contrary to evidence for inconsistent pairwise comparison matrices that limits its application.

This new approach uses two optimistic and pessimistic DEA models to obtain the best local priorities from a pairwise comparison matrix, regardless of whether it is fully consistent or not. Some numerical examples, including a real application of AHP for selecting an innovation team for a university, are provided to specify the advantages of the proposed approach and its potential applications.

Originality/Value:

 The double-frontier DEA approach generates true weights for fully consistent pairwise comparison matrices and best local priorities for inconsistent pairwise comparison matrices, that are logical and fit subjective judgments of decision-makers.