Efficient Mining of High Utility Patterns over Data Streams with a Sliding Window Method

High utility pattern (HUP) mining over data streams has become a challenging research issue in data mining. The existing sliding window-based HUP mining algorithms over stream data suffer from the level-wise candidate generation-and-test problem. Therefore, they need a large amount of execution time and memory. Moreover, their data structures are not suitable for interactive mining. To solve these problems of the existing algorithms, in this paper, we propose a new tree structure, called HUS-tree (High Utility Stream tree) and a novel algorithm, called HUPMS (HOP Mining over Stream data), for sliding window-based HUP mining over data streams. By capturing the important information of the stream data into an HUS-tree, our HUPMS algorithm can mine all the HUPs in the current window with a pattern growth approach. Moreover, HUS-tree is very efficient for interactive mining. Extensive performance analyses show that our algorithm significantly outperforms the existing sliding window-based HUP mining algorithms.