Efficient approach of recent high utility stream pattern mining with indexed list structure and pruning strategy considering arrival times of transactions

摘要: Abstract One of various pattern mining techniques, the High Utility Pattern Mining (HUPM) is a method for finding meaningful patterns from non-binary databases by considering characteristics items. Recently, new data continues to flow over time in diverse fields such as sales market, heartbeat sensor data, and social network service. Since these have feature that recently generated higher influence than old research has been focused on how efficiently extract hidden knowledge time-sensitive databases. In this paper, we propose indexed list-based algorithm mines recent high utility arrival inserted an environment where continuously accumulated. other words, treat importance our algorithms reduces values transactions according applying damped window model concept. Moreover, carry out experiments compare with state-of-the-art using real synthetic datasets circumstances. Experimental results show outperforms competitors terms execution time, memory usage, scalability test.