AI engineering glossary · Time series recsys
What is ranking stage?
Ranking stage: The stage after candidate generation in which a heavier model scores each shortlisted item using rich features and orders them by predicted usefulness. Because it only handles hundreds of items, it can afford complex models.
Ranking stage: an example
A gradient boosted model scores 500 candidates on predicted click and watch time and sorts them.
Related terms
More Time series recsys terms
- RankNet
- Re-ranking stage
- Recommender system
- Recursive forecasting
- Rolling window feature
- SARIMA
- SARIMAX
- Seasonal differencing
Where you learn it
Ranking stage is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.