Recommender Systems
Recommender systems select useful items from a large catalog for a person or situation. They combine item information with observed behavior to suggest products, videos, music, articles, and other items.
itArtificial intelligence and machine learning | OpenSkills.info
Course pathWalk it in order
Look it upDip in anytime
Go furtherLeaves this page
Intro
Recommender Systems
A recommender system chooses a small set of items from a larger catalog. It can suggest related products, order a feed, or select the next track. The output is a ranking decision made from incomplete evidence, not a fact about a person.
Continue the course
This section is part of the paid course.
See pricing to subscribe, or log in if you already have access.
Where this skill leads
Relevant careers
See how this topic contributes to broader role-level skill maps.
Sources
- https://developers.google.com/machine-learning/recommendation/overview/types
Supports
- Three-stage architecture
- re-ranking constraints
- https://developers.google.com/machine-learning/recommendation/overview/candidate-generation
Supports
- Filtering approaches
- embeddings
- similarity measures
- https://developers.google.com/machine-learning/recommendation/dnn/scoring
Supports
- Ranking
- objectives
- positional bias
- https://www.tensorflow.org/recommenders/examples/basic_retrieval
Supports
- Two-tower retrieval
- explicit and implicit feedback
- https://github.com/grahamjenson/list_of_recommender_systems
Supports
- RecBole
- LensKit
- NVIDIA Merlin selections