Sequential pattern mining, which discovers the correlation relationships from the ordered list of events, is an important research field in data mining area. In this paper, I develop a Tree Based Incremental Sequential Pattern Mining algorithm which can generate sequential patterns from the Sequential Pattern Tree recursively. This algorithm builds a Sequential Pattern Tree for both frequent and non-frequent items. It requires only one scan of database to build the tree which can reduce the

more »

... construction time considerably. The main advantage of this algorithm is to mine the complete set of sequential patterns from the Sequential Pattern Tree without generating any intermediate projected tree. It does not generate unnecessary candidate sequences and not require repeated scanning the original database. It also supports incremental mining. While the new sequences are updated, the already existing tree is revised for the updated sequences and then, mines the updated tree for the new frequent subsequences. I have compared the proposed approach with three state-of-the-art algorithms and the performance study shows that, Tree Based Sequential Pattern Mining algorithm is much faster than existing Apriori based GSP algorithm and also faster than existing PrefixSpan and FUSP-Tree algorithm. For incremental mining, the proposed approach outperforms both GSP and PrefixSpan.