An efficient for discovery of frequent itemsets

Association rule mining is a well researched method for discovering interesting relations between variables in large databases. The first phase of association rule mining is the discovery of frequent itemsets which is a critical step and plays important role in many data mining tasks. The existing algorithms for finding frequent itemsets suffer from many problems related to memory and computational cost. In this paper, we propose a new algorithm ILLT (Indexed Limited Level Tree) which gets frequent itemsets efficiently in the given database without doing multiple scans and extensive computation. ILLT algorithm works in two phases. First, the transactional data is converted into three level compact tree structures. Then, these trees are scanned to discover the frequent itemsets. Experimental status shows the effectiveness of the algorithm in mining frequent itemsets.