Uncovering Hidden Associations Through Negative Itemsets Correlations

Abstract

Most algorithms and approaches dealing with data mining in general and especially those focusing on the task of association rule mining have assumed all items to be only positively correlated, and looked only into the items that remained finally in a shopping basket. Very few works have proposed the existence of negative correlations between items, based though on the absence of items from transactions rather than on their actual removals. In this specific chapter we look into mining that takes into consideration valuable information from rejected items and propose various alternatives for taking the specific items into account efficiently. Finally we provide experimental evidence on the existence and significance of these items.