A new associative classification method by integrating CMAR and an evolutionary three-layers structure

The association rules have been demonstrated to be useful for classification, like CBA, CMAR. However, the rule mining procedure does not focus on classification, and most of the rules will be pruned in classification. As a result, if we could directly mine the classification association rules, the time will be saved. Meanwhile, we could expect even better accuracy because the mining procedure itself considers the classification. In this paper, we build a novel evolutionary method, named EvoCMAR, to directly mine classification association rules.