Date clustering using Principal Component Analysis and Particle Swarm Optimization

By analyzing the actuality of the data mining in ecommerce environment, and considering the complexity and the curse of dimensionality about extracting the implicit and unknown knowledge brought by the massive and high-dimensional data. Based on the K-means clustering, Particle Swarm Optimization (PSO) clustering and hybrid PSO clustering algorithm, this paper presented a model which combined Principal Component Analysis (PCA) with hybrid PSO to cluster data. The interrelated data have been processed by Principal Component Analysis; the results of PCA are input data for hybrid PSO clustering algorithms. It not only reduced the dimension of input variables and the scales of clustering, but also reserved the main information of original variables and eliminated the multicollinearity between the variables. It offered an effective model method for data clustering which has characters like massive, high-dimensional and heterogeneous.