Football video recommendation system with automatic rating based on user behavior

With the rapid development of information technology, video has become one of the most frequently media used to obtain information, while football is also in a similar situation. With the increasing network traffic in football video, it is becoming a valuable question to recommend football videos which users like to users. In this paper, the multiple linear regression model is used to fit the user's preference to the video so that the user's preference can be automatically calculated by analyzing a series of user's behavior of video without the user's rating action. Then use the data obtained above to do the video recommendation based on the collaborative filtering algorithm on the Spark platform. Finally, adjust the parameters of each model by analyzing the experiments, so that the accuracy of the model can be achieved better, after which this implicit score calculation method proved to be effective and precise.