Sequential Pattern Mining by Pattern-Growth: Principles and Extensions

Sequential pattern mining is an important data mining problem with broad applications. However, it is also a challenging problem since the mining may have to generate or examine a combinatorially explosive number of intermediate subsequences. Recent studies have developed two major classes of sequential pattern mining methods: (1) a candidate generation-and-test approach, represented by (i) GSP [30], a horizontal format-based sequential pattern mining method, and (ii) SPADE [36], a vertical format-based method; and (2) a sequential pattern growth method, represented by PrefixSpan [26] and its further extensions, such as CloSpan for mining closed sequential patterns [35]. In this study, we perform a systematic introduction and presentation of the pattern-growth methodology and study its principles and extensions. We first introduce two interesting pattern growth algorithms, FreeSpan [11] and PrefixSpan [26], for efficient sequential pattern mining. Then we introduce CloSpan for mining closed sequential patterns. Their relative performance in large sequence databases is presented and analyzed. The various kinds of extension of these methods for (1) mining constraint-based sequential patterns, (2) mining multi-level, multi-dimensional sequential patterns, (3) mining top-k closed sequential patterns, and (4) their applications in bio-sequence pattern analysis and clustering sequences are also discussed in the paper.