Proposition of Relative Confidence for Exploration of Meaningful Association Rules

Association rule mining searches for interesting relationships among items in a given database. One of the popular approaches to association rule exploration is rule ranking using interestingness measures. Good measures also allow the time and space costs of the mining process to be reduced. In recent years, a lot of work has been done in quantifying interestingness. As a result, several measures that view interestingness from different perspectives have been proposed and developed. In this paper, we propose a relative confidence as an objective interestingness measure. This measure is the same as a relative risk in medical science, but the mining of relative risk patterns has never been investigated before. So we investigate the conditions of interestingness measures and some useful properties, and compare some properties of relative confidence and confidence through a few experiments.