PCAR: An Efficient Approach for Mining Association Rules

A lot of existing algorithms used for mining association rules identify frequent itemsets by the method of bottom-up combination of smaller frequent itemsets or top-down decomposing of larger infrequent itemsets, these methods result the large volumes of candidate itemsets. Actually as the supersets of infrequent items are infrequent itemsets, this paper presents a new efficient method, namely pruning-classification association rule (PCAR). PCAR combines minimum frequency items with minimum frequency itemsets. It firstly deletes infrequent items from itemsets, then classifies itemsets based on frequency of itemsets, finally discovers frequent itemsets. The number of candidate itemsets is greatly reduced and itemsets need not to be combined or decomposed, therefore, operation time and memory requirement could be decreased accordingly. This method has significant advantage in mining association rule at large volumes of items and small frequency of itemsets. It is proved by experiments that PCAR outperforms the well-known Apriori and CBAR algorithms.