ACORI: a novel ACO algorithm for rule induction

RIPPER is certainly one of the best rule induction algorithms. In RIPPER, the order in which the rules are learned is important because the first rule to be fired determines the class of the instance. However, the correct class may be identified by another rule further down the list, which is ignored and, thus never examined. This paper offers a contribution to address the mentioned shortcoming. An Ant Colony Optimization (ACO) algorithm is developed for finding the optimal order of rules in the decision list. This algorithm is called ACO for Rule Induction (ACORI). To the best of our knowledge, this is the first paper that devises an optimization method to determine the (near) optimal order of rules in the decision list. The performance of the proposed algorithm is compared to that of RIPPER using 10 data sets. Experimental results and non-parametric statistical tests show that the proposed algorithm significantly outperforms the original RIPPER.