AI engineering glossary · Time series recsys
What is multi-stage recommender pipeline?
Multi-stage recommender pipeline (also called Recommendation funnel): A design that passes items through successive stages, usually retrieval, ranking and re-ranking, each with fewer items and costlier models. It balances quality with latency and compute at large catalogue sizes.
Multi-stage recommender pipeline: an example
10 million items to 1,000 to 100 to the 20 shown, in under 200 milliseconds.
Related terms
More Time series recsys terms
- Multi-step forecasting
- Multiplicative decomposition
- N-BEATS
- Naive forecast
- Novelty
- Pairwise ranking
- Partial autocorrelation function
- PatchTST
Where you learn it
Multi-stage recommender pipeline is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.