Personalized Context-aware Recommendation Approach for Web Services

With the increasing number of Web services, the goal of consumers becomes to discover and use services that lead to their experiencing the highest quality. Quality of Service (QoS) is important to evaluate the QoS performance of services to differentiate the qualities of service candidates. QoS is highly related to context information since service consumers are typically distributed in different geographical locations. Their experience is usually different. Invoking a huge number of Web services for consumers to predict the quality is time-consuming, resourceconsuming, and sometimes even impractical. To address the challenge, this paper proposes a personalized context-aware recommendation approach for predicting the QoS of Web services and designs a prediction framework. This algorithm is a hybrid of the model-based and memory-based collaborative filtering algorithms. In our experiment, we collect QoS information from geographically distributed service consumers through the framework. Based on the QoS and context information, we predict the quality of services. As a result, we can obtain a list of recommended services for selection. Finally, the experiment shows that the algorithm using context information achieves better prediction.