Updating Generalized Association Rules with Evolving Taxonomies

Abstract

Mining generalized association rules between items in the presence of taxonomy has been recognized as an important model in data mining. Earlier work on mining generalized association rules confined the taxonomy to be static. However, the taxonomy of items cannot be kept unchanged all the time. Some items will be sifted from one hierarchy tree to another for more suitable classification or be abandoned from the taxonomy if they will not be produced any more; new born items will also be added into the taxonomy. Under these circumstances, how to update the discovered generalized association rules effectively is a crucial task. In this paper, we examine this problem and propose a novel algorithm, called Taxo_UP, to update the discovered frequent itemsets. Empirical evaluation shows that the proposed algorithm is very effective and has good linear scale-up characteristic.