Spurred by services computing and Web 2.0, more and more mashups are emerging on the Internet. The overwhelming mashups become too large to be effectively recommended by traditional methods. In view of this challenge, we propose a clustering-based collaborative filtering approach for mashup recommendation over big data. This approach mainly divided into two phases: clustering and collaborative filtering. By using clustering techniques, the data size is reduced so that the computation time of collaborative filtering algorithm is decreased significantly. Several experiments are done to verify the efficient of the proposed approach at the end of this paper.
展开▼
