Hybrid recommendation and parallelization of movies based on spark

摘要

With the exponential growth of Internet data, the traditional stand-alone computational model has been unable to solve the real-time precise recommendation items in a complex and huge data, and the defect of traditional recommendation algorithm has become more obvious, this paper studies the collaborative filtering algorithm and matrix decomposition method, designs a parallel computing architecture based on spark, and a movie recommendation based on hybrid recommendation algorithm [1], the experimental results show that in a certain extent improves the recommendation accuracy and scalability, and has good acceleration effect.