We present an efficient algorithm (UWEP) for updating large itemsets when new transactions are added to the set of old transactions. UWEP employs a dynamic lookahead strategy in updating the existing large itemsets by detecting and removing those that will no longer remain large after the contribution of the new set of transactions. It differs from the other update algorithms by scanning the existing database at most once and the new database exactly once. Moreover, it generates and counts the minimum number of candidates in the new database. The experiments on synthetic data show that UWEP outperforms the existing algorithms in terms of the candidates generated and counted.

No abstract