Authors: Nishant Singh, Sudhanshu Kumar, Shushant Mani Tripathi, Manisha Pundir
Abstract: With the rapid growth of digital streaming platforms, users are exposed to a vast amount of movie content, making it difficult to identify relevant choices. This paper presents a Content-Based Movie Recommendation System that suggests movies based on their inherent features such as genre, cast, and keywords. The proposed system utilizes Machine Learning techniques, including TF-IDF (Term Frequency–Inverse Document Frequency) or Count Vectorization for feature extraction and Cosine Similarity for measuring similarity between movies. Unlike collaborative filtering methods, the system does not rely on user interaction data, thereby effectively addressing the cold start problem for new users. The model processes a structured movie dataset, converts textual data into numerical vectors, and generates recommendations based on similarity scores. The system is implemented using Python and deployed using Streamlit, providing an interactive and user-friendly interface. Experimental results demonstrate that the proposed system can efficiently generate accurate and relevant movie recommendations in real time. This approach highlights the effectiveness of content-based filtering techniques in enhancing user experience and improving content discovery in modern digital platforms.
