AI engineering glossary · Time series recsys
What is pairwise ranking?
Pairwise ranking: A learning-to-rank approach whose loss compares two items at a time and encourages the more relevant one to score higher. It focuses on relative order, though it treats all mistakes in pairs equally regardless of list position.
Pairwise ranking: an example
For results A (relevant) and B (not), penalise the model if score(B) is not below score(A).
Related terms
More Time series recsys terms
- Partial autocorrelation function
- PatchTST
- Pointwise ranking
- Popularity bias
- Prediction interval
- Probabilistic forecasting
- Prophet
- Quantile forecast
Where you learn it
Pairwise ranking is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.