Collaborative Filtering
A recommendation technique that predicts user preferences based on the collective behavior of many users, assuming that users who agreed in the past will agree in the future.
Types
User-based: Find similar users, recommend what they liked. Item-based: Find similar items to what the user liked. Matrix factorization: Decompose the user-item interaction matrix to find latent factors.
Applications
Netflix recommendations, Spotify Discover Weekly, Amazon product suggestions, and social media feed ranking. Often combined with content-based filtering in hybrid systems.