An Effcient Algorithm for Mining Association Rules In Massive Datasets
Data mining, also known as Knowledge Discovery in Databases (KDD) is one of the most important and interesting research areas in 21st century. Frequent pattern discovery is one of the important techniques in data mining. The application includes Medicine, Telecommunications and World Wide Web. Nowadays frequent pattern discovery research focuses on finding co-occurrence relationships between items. Apriori algorithm is a classical algorithm for association rule mining. Lots of algorithms for mining association rules and their mutations are proposed on the basis of Apriori algorithm. Most of the previous algorithms Apriori-like algorithm which generates candidates and improving algorithm strategy and structure but at the same time many of the researchers not concentrate on the structure of database. In this research paper, it has been proposed an improved algorithm for mining frequent patterns in large datasets using transposition of the database with minor modification of the Apriori-like algorithm. The main advantage of the proposed method is the database stores in transposed form and in each iteration database is filtered and reduced by generating the transaction id for each pattern. The proposed method reduces the huge computing time and also decreases the database size. Several experiments on real-life data show that the proposed algorithm is very much faster than existing Apriori-like algorithms. Hence the proposed method is very much suitable for the discovering frequent patterns from large datasets.
