CORER: A New Rule Generator Classifier

Abstract

Rule-based classifiers have been successfully applied in data mining applications. In this Paper, we have proposed a novel rule generator classifier called CORER (Colonial competitive Rule-based classifier) to improve the accuracy of data classification. The proposed classifier works based on CCA (Colonial Competitive Algorithm), a recently-developed evolutionary optimization algorithm. In order to approve the CORER capability in various domains, four different datasets from UCI machine learning database repository have been applied. To evaluate CORER performance, we compared our results with some other well-known classification methods, such as C4.5, CN.2, ID3 and naïve bayes which brings about superior results. Our findings lead us to believe that CORER may provide better performance for some critic domains which need more precise classifiers.