A machine learning approach to predict movie box-office success

Abstract

Making a prediction of society’s reaction to a new product in the sense of popularity and adaption rate has become an emerging field of data analysis. The motion picture industry is a multi-billion dollar business. And there is a huge amount of data related to movies is available over the internet and that is why it is an interesting topic for data analysis. Machine learning is a novel approach for analyzing data. Our paper proposes a decision support system for movie investment sector using machine learning techniques. In that case, our system will help investors related with this business to avoid investment risks. The system will predict an approximate success rate of a movie based on its profitability by analyzing historical data from different sources like IMDb, Rotten Tomato, Box Office Mojo and Meta Critic. Using different machine learning algorithms, Natural Language Processing and other techniques the system will predict a movie box office profit based on some features like who are the cast and director members, budget, movie release time, various types of movie rating, movie reviews and then process that data for classification.