Application of Bayesian confirmation measures for mining rules from support-confidence pareto-optimal set

We investigate a monotone link between Bayesian confirmation measures and rule support and confidence. In particular, we prove that two confirmation measures enjoying some desirable properties are monotonically dependent on at least one of the classic dimensions being rule support and confidence. As the confidence measure is unable to identify and eliminate non-interesting rules, for which a premise does not confirm a conclusion, we propose to substitute the confidence for one of the considered confirmation measures. We also provide general conclusions for the monotone link between any confirmation measure enjoying some desirable properties and rule support and confidence.