Scalable and efficient method for mining association rules

Association rules mining (ARM) algorithms have been extensively researched in the last decade. Therefore, numerous algorithms were proposed to discover frequent itemsets and then mine association rules. This paper will present an efficient ARM algorithm by proposing a new technique to generate association rules from a huge set of items, which depends on the concepts of clustering and graph data structure, this new algorithm will be named clustering and graph-based rule mining (CGAR). The CGAR method is to create a cluster table by scanning the database only once, and then clustering the transactions into clusters according to their length. The frequent 1-itemsets will be extracted directly by scanning the cluster table. To obtain frequent k-itemsets, where k ges 2, we build directed graphs for each cluster in the case of very huge amount of transactions. This approach reduces main memory requirement since it considers only a small cluster at a time and hence it is scalable for any large size of the database. Experiments show that our algorithm outperforms other rule mining algorithms.