Hybrid Movie Recommendation System Using Machine Learning

Every year new movies are released with a varied story-line or a genre which could be of potential interest to viewers. Various online movie or video streaming platforms can keep the customers engaged by recommending movies of the viewer's preference. A key research challenge for Recommender engines is make more targeted recommendations. This paper presents Filtering approaches including Content-based, which recommends items (movies) to the user (viewer) based on their previous history/ preferences and Collaborative-based which uses opinions and actions of other similar users (viewers) to recommend items (movies). In Collaborative filtering, User-based, Item based, SVD, and SVD++ algorithms have been implemented and the performance evaluated. Finally, a hybrid recommendation engine that stacks both the Content-based and SVD filtering models is shown to have optimal performance and improved movie recommendations to retain active viewer engagement with the service.