ApproxMAP: Approximate Mining of Consensus Sequential Patterns

Sequential pattern mining is an important data mining task with broad applications. However, conventional methods may meet inherent difficulties in mining databases with long sequences and noise. They may generate a huge number of short and trivial patterns but fail to find interesting patterns approximately shared by many sequences. To attack these problems, in this paper, we propose the theme of approximate sequential pattern mining roughly defined as identifying patterns approximately shared by many sequences. We present an efficient and effective algorithm, ApproxMAP (for APPROXimate Multiple Alignment Pattern mining), to mine consensus patterns from large sequence databases. The method works in two steps. First, sequences are clustered by similarity. Then, consensus patterns are mined directly from each cluster through multiple alignment. A novel structure called weighted sequence is used to compress the alignment result. For each cluster, the longest consensus pattern best representing the cluster is generated from its weighted sequence. Our extensive experimental results on both synthetic and real data sets show that ApproxMAP is robust to noise and both effective and efficient in mining approximate sequential patterns from noisy sequence databases with lengthy sequences. In particular, we report a successful case of mining a real data set which triggered important investigations in welfare services.