Extraction incrémentale de séquences fréquentes dans un flux d'itemsets

Abstract : We present a complete and correct incremental algorithm for mining frequent sequences in a sliding window over a stream of itemsets. It relies on a representation of frequent sequences inspired by the PSP algorithm and on an original method for counting the minimal occurrences of a sequence. Experiments made on simulated and real data show that our incremental algorithm significantly improves the computation time compared to a non-incremental approach.