A novel method of online trading customer classification

Correctly and effectively customer classification according to their characteristics and behaviors will be the most important resource for electronic marketing and online trading of network enterprises. Aiming at the shortages of the existing K-means algorithm of data-mining for customer classification, this paper advances a new customer classification algorithm through improving the existing K-means algorithm. Firstly, the paper designs 21 customer classification indicators based on consumer characteristics and behaviors analysis, including customer characteristics type variables and customer behaviors type variables; then, limitation of K-means algorithm is analyzed; following, corresponding improvements for K-means algorithm are advanced including improvement of K-means algorithm principle, improvement of initial classification centers selection and improvement of the flow of Kmeans algorithm. Finally, the experimental results verify that the new algorithm can improve effectiveness and validity of customer classification when used for classifying network trading customers practically.