Vienna University of Economics and Business Administration

The idea of empowering classical association rules by combining them with fuzzy set theory has already been around since several years. The original idea derives from attempts to deal with quantitative attributes in a database, where subdivision of the quantitative values into crisp sets would lead to overor underestimating values near the borders. Fuzzy sets can overcome that problem by allowing partial memberships to the different sets. Fuzzy set theory provides the tools needed to do the computations in order to be able to deal with the different data structure. This paper will give an introduction to association rules and fuzzy set theory, combining the approaches to enable the mining of fuzzy association rules. Different approaches to fuzzy association rules exist, each of which is presented. Even though a lot of research has been done on the topic and algorithms have been proposed, not many programs provide the functionality yet. In the proceeding of this thesis, a package has been developed which can be applied on quantitative data and demonstrate the mining of fuzzy association rules.