Itemsets Using Bayesian Networks as Background Knowledge

The paper presents a method for pruning frequent itemsets based on background knowledge represented by a Bayesian network. The interestingness of an itemset is dened as the absolute dierence between its support estimated from data and from the Bayesian network. Ecien t algorithms are pre- sented for nding interestingness of a collection of frequent itemsets, and for nding all attribute sets with a given mini- mum interestingness. Practical usefulness of the algorithms and their eciency have been veried experimentally.