Algorithms for Mining Association Rules for Binary Segmentations of Huge Categorical Databases

摘要

We consider the problem of finding association rules that make nearly optimal binary segmentations of huge categorical databases. The optimality of segmentation is defined by an objective function suitable for the user's objective. An objective function is usually defined in terms of the distribution of a given target attribute. Our goal is to find association rules that split databases into two subsets, optimizing the value of an objective function.