A multicriteria classification approach based on pairwise comparisons

Classification refers to the assignment of a set of alternatives into predefined homogeneous classes. Most of the existing classification methodologies are based on absolute comparisons among the alternatives and some reference profiles (cut-off points) that discriminate the classes. This paper proposes a new approach that involves pairwise comparisons based on the multicriteria decision aid paradigm. The basis of the methodology is a preference relation that is used to perform pairwise comparisons among the alternatives. The criteria weights used to construct the preference relation are specified using a reference set of alternatives (training sample) on the basis of linear programming techniques.