Entropy based broadband user service behavior analysis

Abstract

With the rapid development of Internet, network user behavior analysis is getting more and more attention. In this paper, an algorithm combining entropy concept and clustering method is proposed to analyze current broadband users' usage modes of network services, providing a strong support for further analysis or commercial applications. This algorithm can complete the process of division or clustering automatically, without requiring user to input any parameters associated with clustering. And it also can adapt to data set with different shape and size. Experiments have shown promising results when applying this algorithm to classify network users.