Collaborative Web Service QoS Prediction via Location-Aware Matrix Factorization and Unbalanced Distribution

QoS prediction is critical to Web service selection and recommendation. This paper proposes a location-aware collaborative approach to QoS prediction of Web services by utilizing the past Web service usage history of service users, which avoids expensive and time-consuming Web service invocations. We first acquire and process client-side spatial location information. Then, an approach, which integrates spatial location constraint and LFM method and considers unbalanced distribution of data, is designed to achieve higher prediction accuracy for Web service QoS value based on the collected QoS data and location information. To validate our approach, large-scale experiments are conducted based on a real-world Web service dataset, WSDream. The results show that our proposed approach achieves higher prediction accuracy than other approaches.