User Classification Prediction Research Based on Clustering SVM

Abstract

Users interest discovery can be belonged to category of classification knowledge discovery, which can divide user information need into two groups as interested group and uninterested group by classification forecast analysis of user information need which reflects historical visiting information behavior of user. After analysis the use of a several methods of user classification prediction, this paper presents a modified model combining clustering algorithm was presented for improving the forecasting accuracy of SVM. The efficiency of the proposed method was tested by the user access informations log data. The results have shown that the higher accuracy is expressed in this proposed model, and it is applicable to practice.