Maintaining Pre-large FUSP Trees for Record Deletion

In the past, a pre-large fast-updated sequential pattern tree (pre-large FUSP tree) structure was proposed to effectively handle newly inserted customer sequences for data mining. Since data deletion also commonly occurs in real applications, in this paper, we thus propose a maintenance algorithm for pre-large FUSP trees when records are deleted from the mined database. Pre-large sequences act like buffers and are used to reduce the movement of sequences directly from large to small and vice-versa when records are deleted. Experimental results also show that the proposed pre-large FUSP-tree maintenance algorithm for record deletion has a good performance when compared to the batch maintenance algorithm.