A Personalized Web Service Quality Prediction Approach Based on Invoked Feature Model

With the number of Web services increasing exponentially, many Web services available have very similar functionality. One approach to identify the most suitable services for a user is to evaluate the QoS of these services. A personalized QoS prediction method is proposed which exploits network, server environment and user input. It analyzes users’ previous behaviors on the Web and extracts the service invoked feature patterns, and then predicts QoS through the information under the invoked feature patterns and user invoking features. Experimental results show that the proposed method can improve the accuracy of the QoS prediction significantly.