Statistical Strategies for Pruning All the Uninteresting Association Rules
Gemma Casas-Garriga
European Conference on Artificial Intelligence 2004.

Abstract

We propose a general framework to formalize the pro­ blem of capturing the intensity of implication for association rules through statistical metrics. In this framework we present properties that influence the interestingness of a rule, analyze the conditions that lead a measure to perform a perfect prune at a time, and define a final proper order to sort the surviving rules. We will discuss why none of the currently employed measures can capture objective inte­ restingness, and just the combination of some of them in a multi­step fashion, can be reliable. In contrast, we propose a new simple mo­ dification of the Pearson coefficient that will meet all the necessary requirements. We statistically infer the convenient cut­off threshold for this new metric by empirically describing its distribution function through simulation. Experiments show a promising behaviour of our proposal.

Postscript - Requires a viewer, such as GhostView

[Edit]