An Enhanced Content-Based Movie Recommendation System Using SVD and Cosine Similarity

With the increasing availability of digital content, selecting relevant movies has become a challenging task for users. To address this issue, we propose a Content-Based Movie Recommendation System that enhances recommendation accuracy using Singular Value Decomposition (SVD) and Cosine Similarity. The system leverages movie attributes such as genre, cast, and plot details from the TMDB dataset to generate personalized recommendations. By applying SVD, the system reduces dimensionality and captures latent relationships between movies, while Cosine Similarity measures closeness between feature vectors to suggest relevant films. Unlike collaborative filtering, our approach does not rely on user interactions, making it effective even for new or unrated movies. Additionally, a real-time chat room feature allows users to engage in discussions about movies, fostering a sense of community and aiding discovery. This method enhances the recommendation process, improving user experience by reducing search time and promoting diverse movie exploration.