Developed a collaborative filtering recommendation system aimed at suggesting movies based on user preferences. The system analyzes user ratings and applies filtering techniques to generate personalized recommendations. Key Features: Implemented both user-based and item-based collaborative filtering techniques. Analyzed over 100,000 user ratings to tailor personalized movie recommendations. Enhanced system performance by integrating content-based filtering, considering 20+ genres and movie tags. Built a web interface using Flask with an average response time of less than 1 second.
Jan 01, 2023 - Dec 31, 2023