Incremental Mining Item Sets Based on H-mine and XML

Abstract

Efficient discovery of association rules in large database is a well studied problem and several approaches have been proposed. However, the previously proposed methods still encounter some performance bottlenecks when mining databases is updated, such as inserted and deleted. In this paper, we propose an incremental updating technique based on H-mine and xml, for the maintenance of association rules when new transaction data is added to a transaction database. A performance evaluation shows that our algorithm is available and scalable.