A New Self-Organizing Model and its Application in Online Trading Customer Classification

Hankun Ye

School of International Trade and Economics Jiangxi University of Finance and Economics Nanchang, China

Abstract: 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, a new online trading customer classification algorithm is advanced based on combination of the K-means Self-Organizing Feature Map (SOM) algorithms. Firstly, based on consumer characteristics and behaviors analysis, the paper designs 21 customer classification indicators including customer characteristics type variables and customer behaviors type variables. Secondly, the limitation of K-means algorithm is analyzed ; Third, SOM & K-means Combination-Based customer Classification algorithms is advanced to overcome the shortage of the K-means classification algorithm and takes advantage of powerful classification ability of the algorithm to classify online trading customer. 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.

Keywords: Electronic marketing; Customer classification; K_means algorithm; Consumer characteristics analysis; Customer behaviors analysis