ABSTRACT
Data mining techniques have been widely applied in many areas. In data mining, clustering analysis has become one of the important tools. Conventional research usually applied multivariate analysis due to its convenience. However, besides multivariate analysis, neural networks and genetic algorithms are also feasible for this purpose. Thus, this study intends to propose a novel approach which integrates the ART2 and genetic algorithm based K-means for clustering analysis. A comparison of proposed approach is made with the integration of ART2 and K-means. The simulated results showed that the proposed approach outperforms the latter.