Scoring Models

Most recommendation pipelines are built around a scoring model that scores items for a recommendation query (e.g., user). Standard top-N recommendation uses these scores to rank items, and they can be used as inputs into other techniques such as samplers and rerankers. Scorers are almost always Trainable, and by convention are named XYZScorer. They typically take two inputs, the query (query) and the list of items to score (items).

Scoring models are not limited to traditional pointwise scoring models such as matrix factorization. Many learning-to-rank models are also implemented as scorers, but using a model optimized with a rank-based loss function.

Baseline Scorers

lenskit.basic.BiasScorer	A user-item bias rating prediction model.
lenskit.basic.PopScorer	Score items by their popularity.

Classical Collaborative Filters

lenskit.knn.ItemKNNScorer	Item-item nearest-neighbor collaborative filtering feedback.
lenskit.knn.UserKNNScorer	User-user nearest-neighbor collaborative filtering with ratings.
lenskit.als.BiasedMFScorer	Biased matrix factorization trained with alternating least squares [ZWSP08].
lenskit.als.ImplicitMFScorer	Implicit matrix factorization trained with alternating least squares [HKV08].
lenskit.sklearn.svd.BiasedSVDScorer	Biased matrix factorization for explicit feedback using SciKit-Learn's TruncatedSVD.
lenskit.funksvd.FunkSVDScorer	FunkSVD explicit-feedback matrix factoriation.
lenskit.hpf.HPFScorer	Hierarchical Poisson factorization, provided by hpfrec.

Utility Scorers

These scorers are used to compose more sophisticated pipelines, usually involving multiple pipelines.

lenskit.basic.FallbackScorer

Scoring component that fills in missing scores using a fallback.