An efficient approach for updating the structure for mining frequent patterns

Mining frequent patterns is to discover the groups of items appearing always together excess of a user specified threshold from a large transaction database. However, the transactions will grow rapidly, such that the frequent itemsets may be changed due to the addition of the new transactions. The users may eager for getting the latest frequent itemsets from the updated database as soon as possible in order to make the best decision. Therefore, it has become an important issue to propose an efficient method for finding the latest frequent itemsets when the transactions keep being added into the database. For the previous tree-based approaches, they have to re-scan the original database and generate a large tree structure. In this paper, we propose an efficient algorithm which only keeps frequent items in a condensed tree structure. When a set of new transactions is added into the database, our algorithm can efficiently update the tree structure without scanning the original database.