AI engineering glossary · Time series recsys
What is GRU4Rec?
GRU4Rec: A recurrent neural network method for session-based recommendation using gated recurrent units, which reads the sequence of items clicked in a session and predicts the next one, trained with ranking-based losses and session-parallel mini-batches.
GRU4Rec: an example
Feed clicks [phone, case, charger] into the network and it outputs scores for every possible next item.
Related terms
More Time series recsys terms
- Hierarchical forecasting
- Holiday effect
- Holt's linear method
- Holt-Winters method
- Hybrid recommender
- Intermittent demand
- Inverse propensity scoring
- Item-based collaborative filtering
Where you learn it
GRU4Rec is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.