Abstract
Associative classification is a promising new approach that mainly uses association rule mining in classification. However, most associative classification approaches suffer from the huge number of the generated classification rules which takes efforts to select the best ones in order to construct the classifier. In this paper, a new associative classification approach called GARC is proposed. GARC takes advantage of generic basis of association rules in order to reduce the number of association rules without jeopardizing the classification accuracy. Furthermore, since rule ranking plays an important role in the classification task, GARC proposes two different strategies. The latter are based on some interestingness measures that arise from data mining literature. They are used in order to select the best rules during classification of new instances. A detailed description of this method is presented, as well as the experimentation study on 12 benchmark data sets proving that GARC is highly competitive in terms of accuracy in comparison with popular classification approaches.