Web service QoS prediction using improved software source code metrics

Due to the popularity of Web-based applications, various developers have provided an abundance of Web services with similar functionality. Such similarity makes it challenging for users to discover, select, and recommend appropriate Web services for the service-oriented systems. Quality of Service (QoS) has become a vital criterion for service discovery, selection, and recommendation. Unfortunately, service registries cannot ensure the validity of the available quality values of the Web services provided online. Consequently, predicting the Web services’ QoS values has become a vital way to find the most appropriate services. In this paper, we propose a novel methodology for predicting Web service QoS using source code metrics. The core component is aggregating software metrics using inequality distribution from micro level of individual class to the macro level of the entire Web service. We used correlation between QoS and software metrics to train the learning machine. We validate and evaluate our approach using three sets of software quality metrics. Our results show that the proposed methodology can help improve the efficiency for the prediction of QoS properties using its source code metrics.