Mining association rules using fuzzy inference on web data

Abstract

The association rules model is one of most widely used models in data mining. An association rule is an implication of the form X -y Y, where X and Y are a set of items that satisfy two constraints, given by the user, called minimum support (minsup) and minimum confidence (minconf). Normally, the values of minsup and minconf are crisp. In this paper, we analyze how association rules mining is affected when these values are treated as fuzzy. In order to calculate frequent itemsets and to generate association rules, an algorithm based on fuzzy sets is proposed. Using the fuzzy inference system, FUZZYC, the algorithm offers to user an intuitive way for defining and tuning the minconf and minsup parameters.