Incremental mining of Web sequential patterns using PLWAP tree on tolerance MinSupport

This work proposes an algorithm, PL4UP, which uses the PLWAP tree structure to incrementally update Web sequential patterns. PL4UP initially builds a bigger PLWAP tree that includes all sequences in the database with a tolerance support, t, that is a fraction of the database minimum support, s. The position code features of the PLWAP tree are used to efficiently mine this tree to extract both current frequent and nonfrequent sequences, which are likely to become frequent when the database is updated. This approach more quickly updates old frequent patterns without the need to rescan the entire updated database.