Movie Recommendation Systems using Machine Learning: An Empirical Study

Traditional recommendation systems help users find relevant content or products by predicting user preferences based on historical data. This project focuses on analysing and comparing different machine learning-based recommendation systems for movies. We have examined the effectiveness of some of the techniques used in recommending movies to users. A dataset consisting of movie ratings and user information is used to examine the recommendation system's performance. Our study aims to provide insights into different movie recommendation techniques and to identify the most effective approach. After implementation, we have evaluated their performance and did a comparative analysis. Our study reveals that model based collaborative filtering gives the best hit ratio of 0.96 followed by content based filtering. Comparatively, lower hit ratio was found in memory based filtering recommendation systems.