MUSA-INT: Multicriteria customer satisfaction analysis with interacting criteria

We are considering the problem of measuring and analyzing customer satisfaction concerning a product or a service evaluated on multiple criteria. The proposed methodology generalizes the MUSA (MUlticriteria Satisfaction Analysis) method. MUSA is a preference disaggregation method that, following the principle of ordinal regression analysis, finds an additive utility function representing both the comprehensive satisfaction level of a set of customers and a marginal satisfaction level with respect to each criterion. Differently from MUSA, the proposed approach, that we will call MUSA-INT, takes also into account positive and negative interactions among criteria, similarly to the multicriteria method UTAGMS-INT. Our method accepts evaluations on criteria with different ordinal scales which do not need to be transformed into a unique cardinal scale prior to the analysis. Moreover, instead of a single utility function, MUSA-INT can also take into account a set of utility functions representing customers' satisfaction, adopting the robust ordinal regression methodology. An illustrative example shows how the proposed methodology can be applied on a customers’ survey.