How to Interpret AHP/ANP Application Results in a Really Meaningful Manner?

Abstract

Final decision recommendations rely heavily on ranking Decision-Making Units (DMUs), often achieved using Saaty’s Analytic Hierarchy/Network Process (AHP/ANP). AHP/ANP provides precise overall priority scores which decision-makers commonly treat as definitive for ranking purposes. This reliance means that even minimal numerical differences between DMUs are used to determine the final selection. However, this strict adherence to tiny numerical distinctions – disregarding the actual degree of difference – is problematic. Practically, it risks rejecting DMUs whose performance is only slightly inferior, methodologically, it contradicts the qualitative nature of the input (pairwise comparisons) with the quantitative output. This tension raises the question of achieving an adequate qualitative interpretation of the quantitative rankings. To resolve this, the paper proposes clustering approaches to help decision-makers reliably group and discriminate among similar DMUs. These methods aim to justify more informed choices by avoiding spurious precision. The approaches were tested using two diverse decision cases. The results are promising and indicate that these clustering techniques can be useful under certain specific circumstances.