Mining Sequential Patterns Using I-PrefixSpan

Sequential pattern mining is a relatively new data-mining problem with many areas of application. One of its challenges is to develop a highly efficient and scalable method especially when the minimum support threshold gets smaller. Most of the previous works explore Apriori approach which is not efficient in mining plentiful and long patterns. In this paper, we propose an improvement of pattern growth-based PrefixSpan algorithm, called I-PrefixSpan. The general idea of I-PrefixSpan is to use the efficient data structure for general tree-like framework and separator database to reduce the execution time and memory usage. Thus, with I-PrefixSpan there is no in-memory database stored after index set is constructed. The experimental result shows that using Java 2, this method improves the speed of PrefixSpan up to almost two orders of magnitude as well as the memory usage to more than one order of magnitude.