Development of Movie Recommendation System Using Machine Learning

The past ten years have seen a massive influx of data, which has both improved our lives in certain ways and created a paradox of choice in others. It can be very overwhelming to have so many options for everything from what one eats to what to watch. There is a vast amount of data available in the field of media content, especially movies. This abundance is greater than the options available to previous generations. It is challenging for people to locate content that suits their tastes due to the continuously expanding archive of films. By making recommendations for movies based on user interactions or movie attributes, movie recommendation systems address this problem. This paper looks into the development of a movie recommendation system through the use of machine learning techniques in a content-based manner. The system looks at movie attributes like plot keywords, director, genre, and actors to find movies that are comparable to ones a user has already seen and enjoyed. The primary objective is to enhance the user experience by providing tailored recommendations that are based on the essential elements of movies. A content-based approach is used to identify unique features of each movie and recommend similar options to users with similar preferences. We use algorithms such as Text Vectorization and Cosine Similarity to recommend five similar movies based on a user's previous viewing experience. Key Words: Movie Recommendation System, Recommendation Systems, Content Based, Machine Learning, Cosine Similarity