Summaries of Action Rules by Agglomerative Clustering

Abstract

Finding useful rules is an important task of knowledge discovery in data. Most of the researchers on knowledge discovery focused on techniques for generating patterns, such as classification rules, association rules...etc, from a data set. They assume that it is users responsibility to analyze these patterns and infer actionable solutions for specific problems within a given domain. Action rules mining is a technique that automatically assists humans in acquiring useful information from data. In addition to uncovering important patterns, action rules may suggest actions to be taken based on that knowledge and contribute to business strategies and scientific research. The large amounts of knowledge in the form of rules presents a challenge of identifying the essence, the most important or interesting part of high usability. In this paper, we propose a new method for clustering action rules and replacing them by new action rules of a compact form called summaries. This method is based on agglomerative clustering.