Efficient mining of frequent patterns based on a condensed tree structure

초록

Frequent pattern mining has attracted a great deal of interests during the recent surge in Web mining research because it is the basis of many applications such as customer behavior analysis and trend prediction. Researchers have proposed various data structures and algorithms to discover frequently occurring patterns from a given data set. In particular, tree structures have been popular since they can effectively represent the input data set for efficient pattern discovery. In this paper, we propose an efficient tree structure and its associated algorithm that provides a considerable performance improvement over CATS, one of the fastest frequent pattern mining algorithms known to date, in terms of memory usage and processing time. We demonstrate the effectiveness of our algorithm and performance improvement over me existing approach by a series of experiments. © 2014 International Information Institute.

키워드