🎬 MY PUBLICATIONS

🧠 Abstract – Recommendation systems play a pivotal role in personalizing content delivery across digital platforms. In this project, I developed a Movie Recommendation System using Collaborative Filtering and Natural Language Processing (NLP), leveraging the MovieLens 25M dataset. Our system analyzes user preferences and predicts top movie recommendations by computing cosine similarity scores on TF-IDF-transformed titles and employing user-based collaborative filtering to match user behavior patterns. A Netflix-style UI, an interactive widget using ipywidgets, and real-time top 10 recommendations enhance user experience. The model’s accuracy was evaluated using Root Mean Squared Error (RMSE), achieving a low error score of 0.78, indicating strong prediction performance.