21-05-2014, 02:12 PM
3. Fast Discovery of Association Rules
ABSTRACT
In this paper they consider the problem of association rules between items in large database of sales transaction. They present two new algorithms Apriori and AprioriTid for discovering all significant association rule between items in large database of transactions. They compared these algorithms with the previously known algorithms for frequent pattern mining AIS and SETM. In this experi,ental results are presented using synthetic data showing that the proposed algorithms always outperform AIS and SETM. The performance gap increased with the problem size and ranged from a factor of three for small problems to more than an order of magnitude for large problems.