Youtube Video Recommendation using user-based Collaborative Filtering and Graph Neural Networks Approaches to Improve users Personalized Experience

YouTube's video recommendation method stands as a pinnacle in the realm of content discovery in enhancing user engagement on the platform. The User-Based Collaborative Filtering recommendation method relies on a robust foundation of data collection, encompassing user interactions, metadata, and content features. Leveraging advanced deep learning techniques, videos and users are transformed into vectors within a high-dimensional space, forming the basis for understanding complex relationships. The algorithm's training process involves the utilization of vast datasets, allowing the model to discern patterns in user behavior and content preferences. Predictions and rankings are determined in real-time, ensuring adaptability to evolving user tastes. The feedback loop, fueled by user interactions, continuously refines the algorithm, striking a balance between user satisfaction and content diversity. YouTube's commitment to preventing content bubbles is evident in the incorporation of diversity-enhancing strategies, introducing randomness and exploration to broaden user content experiences. Personalization remains a hallmark, tailoring recommendations based on individual user histories, preferences, and interactions. While the recommendation method has significantly improved content discovery and user satisfaction, it is not without challenges. Ethical considerations, privacy concerns, and the need for algorithmic transparency remain focal points in ongoing developments. Looking forward, the future holds exciting possibilities, with emerging technologies poised to shape the evolution of YouTube's video recommendation method