Customer satisfaction analysis has become a hot issue in strategic management. Traditionally the conjoint analysis is used in order to obtain data from the questionnaires to build a collective utility function representing customer preferences. In this paper, we propose an alternative methodology to analyze the data from the questionnaires. Our approach is based on the rough set theory and it aims at representing the preferences of the customers by means of simple decision rules. The interpretation of the decision rules is simpler and more direct than the interpretation of the utility function given by conjoint analysis. The proposed methodology provides also a measure of expected efficiency of strategic interventions aimed at improving the quality of the offered products and services. In this way, our approach supplies an integrated support to customer satisfaction oriented management.