Incremental Data Mining for Sequential Patterns Using Pre-large Sequences

摘要

In this paper, we propose a novel incremental mining algorithm for sequential patterns based on the concept of pre-large sequences to reduce the need for rescanning original databases. Pre-large sequences are defined by a lower support threshold and an upper support threshold. They act as gaps to avoid the movements of sequences directly from large to small and vice-versa. The proposed algorithm does not require rescanning an original database until the accumulative amount of new added customer sequences exceeds a safety bound, which depends on the size of the database. Thus, if the size of a database grows larger, the number of new transactions allowed before database rescanning will be larger too. The proposed approach thus becomes increasingly efficient as a database grows.