Abstract: Quality function deployment (QFD) is becoming a widely used customer-oriented approach to product design. The inherent fuzziness in QFD system makes fuzzy regression more appealing than classical statistical tools. This paper presents a mathematic approach to determine the relation functions between customer requirements and engineering characteristics and correlation functions among engineering characteristics using optimization theory combined with fuzzy regression theory, and furthermore proposes a crisp and a fuzzy decision models for HOQ. The proposed models would be applicable to a wide spectrum of design problems where multiple design criteria and functional design relationships are interacting and/or conflicting in an uncertain and fuzzy product design process and allow a design team to reconcile tradeoffs among the various customer satisfaction levels as well as the inherent fuzziness in the system.