Also known as: Recommendation Systems
Рекомендательная система выбирает небольшой набор вероятно релевантных или желательных элементов для пользователя из гораздо большего каталога. Она может использовать поведение пользователей, атрибуты items, collaborative filtering, ranking models или business rules для рекомендации контента, продуктов или действий.
A system that selects for each user a relatively small set of desirable items from a large corpus. For example, a video recommendation system might recommend two videos from a corpus of 100,000 videos, selecting Casablanca and The Philadelphia Story for one user, and Wonder Woman and Black Panther for another. A video recommendation system might base its recommendations on factors such as: - Movies that similar users have rated or watched. - Genre, directors, actors, target demographic... See the Recommendation Systems course for more information.
A recommendation system is a machine learning-based system that helps users find compelling content in a large corpus. It generates a smaller subset of candidates from a potentially huge corpus, scores and ranks the candidates, and re-ranks the final ranking to take into account additional constraints. For more information, see Recommendation systems overview.