The Popularity of Movies Predict System based on Data Mining Technology for CDN

摘要

In order to guide the strategy of distributing movies on the CDN system, this paper proposes a method which uses data mining techniques to predict the popularity of movies. The popularity of movies which is predicted is more suitable to the current CDN system. We compare the performance of the Bayesian Network and Decision Tree, and find that the Bayesian Network model is more suitable to CDN.