Package org.apache.mahout.cf.taste.impl.recommender.svd

Interface Summary
Factorizer Implementation must be able to create a factorization of a rating matrix
PersistenceStrategy Provides storage for Factorizations
 

Class Summary
AbstractFactorizer base class for Factorizers, provides ID to index mapping
ALSWRFactorizer 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 http://research.yahoo.com/pub/2433
Factorization a factorization of the rating matrix
FilePersistenceStrategy Provides a file-based persistent store.
NoPersistenceStrategy A PersistenceStrategy which does nothing.
ParallelSGDFactorizer Minimalistic implementation of Parallel SGD factorizer based on "Scalable Collaborative Filtering Approaches for Large Recommender Systems" and "Hogwild!: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent"
ParallelSGDFactorizer.PreferenceShuffler  
RatingSGDFactorizer Matrix factorization with user and item biases for rating prediction, trained with plain vanilla SGD
SVDPlusPlusFactorizer SVD++, an enhancement of classical matrix factorization for rating prediction.
SVDRecommender A Recommender that uses matrix factorization (a projection of users and items onto a feature space)
 



Copyright © 2008–2014 The Apache Software Foundation. All rights reserved.