Collaborative filtering locations of users and web services for improving QOS Prediction and accuracy

Abstract

Collaborative Filtering (CF) based Web service recommendation aims to predict missing QoS (Quality-of-Service) values of Web services. The proposed method leverages both locations of users and Web services while choosing similar neighbors for the target user or service. Collaborative Filtering (CF) is widely employed for making Web service recommendation. CF-based Web service aims to predict missing QoS (Quality-of-Service) values of Web services. Although several CF-based web service by using QoS prediction methods. However, the performance still needs development. Firstly, existing QoS prediction methods rarely considers personalized influence of users and services when measuring doing the comparison between users and between services. Secondly, Web service QoS factors, such as throughput and response time, usually depends on the locations of Web services and users. However, existing Web service QoS prediction methods very rarely took this observation into consideration. In this paper, we propose a location-aware personalized collaborative filtering method for Web service recommendation. The proposed method leverages both locations of users and Web services when selecting similar neighbors for the target user or service. To evaluate the performance of our proposed method, we conduct a set of experiments using a real-world Web service dataset. The experimental result proves that our approach improves the QoS computational efficiency and prediction accuracy significantly, compared to previous CF-based methods.