An algorithm for mining association rules using an efficient hashing with transaction trimming

Association rule discovery has emerged as an important problem in data mining. Mining of association rules consists of identifying the frequent itemsets, and then forming conditional implication rules among them. Direct Hashing and Pruning (DHP) algorithm acts as a base for our algorithm in which smaller candidate sets for large 2-itemsets are generated at an early stage. In this paper, we propose an algorithm called Efficient Hashing with Transaction Trimming (EHTT) for finding frequent itemsets in transaction databases. The algorithm uses an efficient hashing technique for generating smaller candidate sets for large 2-itemsets at an earlier stage of the iterations. Generation of large 2-itemsets at an earlier stage reduces the size of the transaction database after trimming and the cost of later iterations will be less when compared to DHP algorithm.