Preference modelling in sorting problems: Multiple criteria decision aid and statistical learning perspectives

Abstract

Many decision problems in a variety of fields such as marketing, quality prediction, and economics correspond to the sorting decision problematic where an ordinal scale is used to express a preference of objects. Both Multiple Criteria Decision Aid and Statistical Learning fields offer methodologies to represent the preference of the decision maker facing the sorting problem, however, there are differences in terminology, objectives, key assumptions, and solution philosophies. In this context, this paper aims to explain these differences as well as similarities and connections between these two fields by reviewing exemplary methodologies in sorting problems. As we discuss, there are significant research opportunities for developing new methodologies by exploiting the strong aspects of these two fields.