A new maintenance algorithm for mining sequential patterns

Mining of sequential patterns is an important issue among the various data mining problems. The problem of maintaining discovered sequential patterns should be paid more attention in the same way. This paper discusses the issue of maintaining discovered sequential patterns when some information is deleted from a sequence database. A new algorithm, called IU/spl I.bar/D, is presented, and the algorithm makes full use of the information obtained from previous mining results to cut down the cost of finding new sequential patterns in an updated database. Experimental analysis shows that the new algorithm is more efficient.