Ranking association rules for classification based on genetic network programming
Guangfei Yang, Shingo Mabu, Kaoru Shimada, Yunlu Gong, Kotaro Hirasawa · 2009
In this paper, we propose a Genetic Network Programming (GNP) based ranking method to improve the accuracy of Classification Based on Association Rule(CBA). We start from an empirical phenomenon, that is, the accuracy could be improved by changing the ranking of rules in CBA. Then, we apply GNP to build a model, namely RuleRank, to find good ranking equations to rank association rules in CBA. The simulation results show that RuleRank could improve the accuracy of CBA effectively.