Enhancing the Performance in Generating Association Rules using Singleton Apriori

Association rule min ing aims to determine the relations among sets of items in transaction database and data repositories. It generates informative patterns from large databases. Apriori algorithm is a very popular algorithm in data min ing for defining the relationships among itemsets. It generates 1, 2, 3,..., n-item candidate sets. Besides, it performs many scans on transactions to find the frequencies of itemsets which determine 1, 2, 3,..., n-item frequent sets. This paper aims to erad icate the generation of candidate itemsets so as to minimize the processing time, memory and the number of scans on the database. Since only those itemsets which occur in a transaction play a vital ro le in determining frequent itemset, the methodology that is proposed in this paper is extracting only single itemsets from each transaction, then 2,3,..., n itemsets are generated from them and their corresponding frequencies are also calculated. Further, each transaction is scanned only once and no candidate itemsets is generated both resulting in minimizing the memory space for storing the scanned itemsets and minimizing the processing time too. Based on the generated itemsets, association ru les are generated using minimum support and confidence.