Web Potential Customer Classification Based on SVM

Abstract

Potential customers are the future sources of profits. The manager can make decisions and manage customer relationship specifically as soon as finding those people. In this paper, a novel support vector machine (SVM) algorithm is used in Web mining, in order to find potential customers who visit the Web sites. And those potential customers are divided into two classes. Support Vector Machine (SVM) constructs an optimal hyperplane utilizing a small set of vectors near boundary. However, when the two-class problem samples are very unbalanced, PSVM tends to fit better the class with more samples and has high error in the class with fewer samples. To address the problem, an improved SVM algorithm, DFP-PSVM is presented in this paper. Computational results indicate that the modified algorithm has a strong capability of classification for the unbalanced samples of the two-class problems.