Collaborative Filtering Video Recommendation Algorithm Based on Mahout
Video recommendation technology can help users find the interesting videos quickly and has become the key of research on social network services. A new Mahout-based collaborative filtering video recommendation algorithm CF_PIU is proposed to resolve the data sparsity and poor scalability of some traditional algorithms such as User-Based and Item-Based. In CF_PIU, a new method is proposed to denote the similarity between users by combining the basic ideas of User-Based and Item-Based; and the similarity is optimized by using the correlation coefficient. Experiment results show that CF_PIU performs better than traditional video recommendation algorithms as UserCF on quality of recommendation.
NETL
NSTL
万方数据
