Comprehensive Evaluation of E-Commerce Websites Based on PCA and SVM

With the increasing use of E-commerce websites, it is gaining more and more attention. The evaluation of E-commerce websites becoming the focus of study. This paper design a comprehensive evaluation indicator system. Adopting principal component analysis method to simplify the indicator system. A evaluation model of customer relationship management system based on support vector machine was presented. Using the idea of decision binary tree, then makes the cut date to be the input information of classifier, and establish multi-classification model. By using the combination of the two methods, we will acquire a more objective and believable evaluation result. The simulation result shows that the model has better accuracy of the classification.