An Efficient Methodology for Mining Generalized Association Rules

Mining association rules is one of the important research issues in data mining. So, many algorithms have been proposed to findassociation rules in databases. However there are many problems in process of mining rules by most of mining algorithms, thequantity of rule and the efficiency of algorithms . one of the most popular algorithms is apriori_like algorithm.In this paper We propose the a generalized association rule base of a database, which not only contains the whole information of allassociation rules, but also has acceptable efficiency by doing the limitation of the apriori time-wasting algorithm for scanning theentire database and searching on the frequent generalized itemsets , and propose an modification on apriori by reducing that wastetime depending on checking only some records in database (by partitioning the database and using new structures namedGgsidevector for each cluster). Experiments were carried out in real data sets aiming to evaluate the efficiency expressed by thegeneralized rules. The analysis showed that our algorithm has better performance than apriori like algorithm, an efficient algorithmfor mining association rules .

کلیدواژه ها:

generalized association rules ، generalized subvector ، cluster table