Implicit Feedback
User behavior data collected indirectly, such as clicks, watch time, or purchase history, used to infer preferences without asking for direct ratings.
Think of It Like This
Like guessing a friend's favorite food by noticing what they always order, rather than asking them directly.
Implicit feedback is abundant but noisy because a user might click an item accidentally or watch a video they dislike. Recommender systems heavily rely on this data since explicit ratings are rare and harder to collect. Specialized loss functions like BPR (Bayesian Personalized Ranking) are often used to train models on this type of data.