An Evolutionary Algorithm for Automated Discovery of Small-Disjunct Rules
In general rule induction algorithms have a bias that favors the discovery of large disjuncts, rather than small disjuncts. In the context of data mining, small disjuncts are rules covering a small number of examples. Due to their nature, small disjuncts are error prone. It correctly classify individually only few examples but, collectively, cover a significant percentage of the set of examples, so that it is important to develop new approaches to cope with the problem of small disjuncts. This paper presents a classification algorithm based on Evolutionary Algorithm (EA) that discovers interesting small-disjunct rules in the form If P Then D. The proposed system specifically designed for discovering rules covering examples belonging to small disjuncts.