A Movie Weekly Box-Office Revenues Prediction Model Based On Online Reviews

To predict the movie weekly box-office revenues, this paper proposes a new prediction model based on ensemble machine learning method. Firstly, we extract some important features from movie online reviews. Then, due to the limited ability of the single machine learning model, an ensemble machine XGboost is employed to predict the movie weekly box-office revenues in this paper. Finally, we collect the movie online reviews from Douban.com, and use about 600 movies to verify the performance of the model. The experimental results show that the effectiveness and practicability of this model.