Interactive discovery of association rules over data streams

To trace the changes of association rules over an online data stream efficiently, this paper proposes two different methods of generating association rules directly over the changing set of currently frequent itemsets. These methods can avoid the drawbacks of the conventional two-step approach and provide an efficient way. The prefix tree itself can be utilized as an index structure for finding the current support of an association rule. While all of the currently frequent itemsets are monitored by the prefix tree, a traversal stack is employed to efficiently enumerate all association rules. In the on-line environment, a user may be interested in finding those association rules whose antecedents or consequents are fixed as a specific itemset. For this purpose, two additional methods, namely Assoc-X and Assoc-Y, are introduced. Finally, the proposed methods are compared by a series of experiments to identify its various characteristics.