Abstract—Among the discovered knowledge, sequential-pattern mining is used to discover the frequent subsequences from a sequence database. Most research handles the static database in batch mode to discover the desired sequential patterns. In the past, the fast updated (FUP) and Fast UPdated 2 (FUP2) concepts were adopted to, respectively, maintain and update the discovered sequential patterns with sequence insertion and sequence deletion based on the designed FUP sequential pattern (FUSP)-tree structure. Based on the FUP or FUP2 concepts, original customer sequences are required to be rescanned if it is necessary to maintain and update the unpromising (small) sequences from the original database. In the past, pre-large concept was designed to keep the prelarge itemsets as the buffer to avoid the database rescan each time whether transaction insertion or deletion in the dynamic databases. In this paper, < Final Year Projects > the prelarge concept is adopted to handle the discovered sequential patterns with sequence deletion. An FUSP tree is first built to keep only the frequent 1-sequences from the original database. The prelarge 1-sequences are also kept in a set for later maintenance approach.
sales on Site11,021