Although different associative classification algorithms have been proposed, as pointed out by [8], none of the available associative algorithm considers the rule dependence problem that will directly influence the classification accuracy of the associative classifier. Since finding the optimal execution order of class association rules (CARs) is a combinational problem, in this paper, instead of finding the optimal execution order of CARs, we propose a polynomial time algorithm to re-rank the execution order of CARs by class priority to reduce the influence of the rule dependency problem. Consequently, the performance (the classification accuracy and recall rate) of the associative classification algorithm can be improved. The experimental results show that the association classifier with our method can get better classification result than that of the association classifier without considering the rule dependence problem.
關聯:
Journal of Computational Information Systems 8(4), pp.1697-1712
