ClaSP : an efficient algorithm for mining frequent closed sequences
Faculty of Sciences. Mathematics and Computer Science
Lecture notes in computer science
, p. 50-61
University of Antwerp
In this paper, we propose a new algorithm, called ClaSP for mining frequent closed sequential patterns in temporal transaction data. Our algorithm uses several efficient search space pruning methods together with a vertical database layout. Experiments on both synthetic and real datasets show that ClaSP outperforms currently well known state of the art methods, such as CloSpan.