IPTV Program Recommendation Based On Combination Strategy

With the development of television technology and communication technology, such as DVB (digital video broadcasting), IPTV, TV-anytime and other technology, to allow more personalized TV service more possible. With the rapid development of information technology at the same time, people repeatedly selected programs every day in hundreds of TV programs. People are faced with a lot of information overload. This means that information overload has been beyond the scope of individual control, which prompted them believe that they may miss a lot of his love of the show. As a new interactive service technology, IPTV has been extensively studding in the field of TV program recommendation, but the sparse of the user-program rating matrix and cold-start problem is a bottleneck that the program recommended accurately.In this paper, a reasonable combination of two recommendation strategies proposed, which explored the sparse and cold-start problem as well as the problem of user interest change over time. This paper achieved content-based filtering section and collaborative filtering section according to the two combination strategies, which effectively solved the cold-start program and over sparse problem and the problem of users interest change over time. The experimental results showed that this combinational recommendation system in optimal parameters compared by using any one of two combination strategies or not using any combination strategy at all. and the reducing range of MAE is [2.7%.3%].The increasing range of precision and recall is [13.8%95.5%] and [0.97.8%]. respectively. The experiment showed better results when using combinational recommendation system in optimal parameters than using each combination strategies individually or not using any combination strategy.