Optimized Weighted Association Rule Mining using Mutual Information on Fuzzy Data

Association rule mining is used to find the frequent item sets in large database. Generally Apriori algorithm used to find association rules for single dimensional database. Due to the candidate set generation in large database, it decreases the mining efficiency. As well as different items having different weight on its transaction. In this paper, we introduce a novel technique, called Weighted Fuzzy Association Rule Mining using Mutual Information (WFARMI), for mining association rules using fuzzy set theory. This algorithm avoids the costly generation of a large number of candidate sets. Mutual Information is used to provide the strong relationship among the attributes and assigning weight on the fuzzy data. The paper concludes with shows that the proposed algorithm is capable of discovering meaningful and useful weighted fuzzy association rules in an effective manner. Also speeding up the mining process and obtaining most of the high confidence.