A fuzzy approach for mining quantitative association rules

During the last ten years, data mining, also known as knowledge discovery in databases, has established its position as a prominent and important research area. Mining association rules is one of the important research problems in data mining. Many algorithms have been proposed to find association rules in databases with quantitative attributes. The algorithms usually discretize the attribute domains into sharp intervals, and then apply simpler algorithms developed for boolean attributes. An example of a quantitative association rule might be 10% of married people between age 50 and 70 have at least 2 cars. Recently, fuzzy sets were suggested to represent intervals with non-sharp boundaries. Using the fuzzy concept, the above example could be rephrased e.g. 10% of married old people have several cars. However, if the fuzzy sets are not well chosen, anomalies may occur. In this paper we tackle this problem by introducing an additional fuzzy normalization process. Then we present the definition of quantitative association rules based on fuzzy set theory and propose a new algorithm for mining fuzzy association rules. The algorithm uses generalized definitions for interest measures. Experimental results show the efficiency of the algorithm for large databases.