NReco.CF.Taste.Impl.Recommender.SVD NamespaceNReco.Recommender Class Library

Public classAbstractFactorizer
Base class for IFactorizers, provides ID to index mapping
Public classALSWRFactorizer
Factorizes the rating matrix using "Alternating-Least-Squares with Weighted-λ-Regularization" as described in "Large-scale Collaborative Filtering for the Netflix Prize" also supports the implicit feedback variant of this approach as described in "Collaborative Filtering for Implicit Feedback Datasets" available at
Public classALSWRFactorizer Features
Public classFactorization
A factorization of the rating matrix
Public classFilePersistenceStrategy
Provides a file-based persistent store.
Public classNoPersistenceStrategy
A IPersistenceStrategy which does nothing.
Public classParallelSGDFactorizer
Public classParallelSGDFactorizer PreferenceShuffler
Public classRatingSGDFactorizer
Matrix factorization with user and item biases for rating prediction, trained with plain vanilla SGD
Public classSVDPlusPlusFactorizer
SVD++, an enhancement of classical matrix factorization for rating prediction. Additionally to using ratings (how did people rate?) for learning, this model also takes into account who rated what. Yehuda Koren: Factorization Meets the Neighborhood: a Multifaceted Collaborative Filtering Model, KDD 2008.
Public classSVDRecommender
A IRecommender that uses matrix factorization (a projection of users and items onto a feature space)

Public interfaceIFactorizer
Implementation must be able to create a factorization of a rating matrix
Public interfaceIPersistenceStrategy
Provides storage for Factorizations