Interaction of Criteria and Robust Ordinal Regression in Bi-polar PROMETHEE Methods

In this paper we consider the bipolar approach to Multiple Criteria Decision Analysis (MCDA). In particular we aggregate positive and negative preferences by means of the bipolar PROMETHEE method. To elicit preferences we consider Robust Ordinal Regression (ROR) that has been recently proposed to derive robust conclusions through the use of the concepts of possible and necessary preferences. It permits to take into account the whole set of preference parameters compatible with the preference information given by the Decision Maker (DM).