Discovering quantitative associations in databases

In this paper, we introduce a technique for mining association rules from quantitative data tables. The proposed method integrates the fuzzy set concept and the Apriori algorithm. In this algorithm, the design of the membership functions avoids discriminating between the importance levels of the points. Additionally, our method incorporates the bias direction of an item from the center of a membership function region. Also, the method emphasizes the distinction between three important parameters: the support of a rule, its strength and its confidence. It avoids missing the distinction between small numbers of occurrences with highly-supported intersections and large numbers of occurrences with low-supported intersections