TNS

Mining sequential rules from sequence databases is an important research problem with wide applications. However, depending on the choice of the thresholds, current algorithms can become very slow and generate an extremely large amount of results or generate too few results, omitting valuable information. Moreover, a large proportion of sequential rules generated are redundant. In previous works, these two problems have been addressed separately. In this paper, we address both by proposing an algorithm for mining top-k non redundant sequential rules.