A QoS prediction approach based on improved collaborative filtering

Consumers need to make prediction on the quality of unused Web services before selecting from a large number of services. Usually, this prediction is made based on other consumers´ experiences. Being aware of the similarity of consumers´ assessment, this paper proposes a QoS prediction approach. This approach calculates the similarity among consumers, and then uses a improved collaborative filtering technology to predicting the QoS of the unused Web services. Experimental results show that with this approach preciseness of QoS prediction for Web services is higher than other prediction approaches, and it has good feasibility and effectiveness.