MyMediaLite  3.08
Classes
Package MyMediaLite.ItemRecommendation

This namespace contains item recommenders and some helper classes for item recommendation. More...

Classes

class  BPRLinear
 Linear model optimized for BPR. More...
class  BPRMF
 Matrix factorization model for item prediction (ranking) optimized for BPR. More...
class  BPRSLIM
 Sparse Linear Methods (SLIM) for item prediction (ranking) optimized for BPR-Opt optimization criterion. More...
class  Extensions
 Class that contains static methods for item prediction. More...
class  ExternalItemRecommender
 Uses externally computed predictions. More...
interface  IFoldInItemRecommender
 Item recommender that allows folding in new users. More...
interface  IIncrementalItemRecommender
 Interface for item recommenders. More...
class  IncrementalItemRecommender
 Base class for item recommenders that support incremental updates. More...
class  ItemAttributeKNN
 k-nearest neighbor (kNN) item-based collaborative filtering using the correlation of the item attibutes More...
class  ItemKNN
 k-nearest neighbor (kNN) item-based collaborative filtering More...
class  ItemRecommender
 Abstract item recommender class that loads the (positive-only implicit feedback) training data into memory and provides flexible access to it. More...
interface  ITransductiveItemRecommender
 Interface for item recommenders that take into account some test data for training. More...
class  KNN
 Base class for item recommenders that use some kind of k-nearest neighbors (kNN) model. More...
class  LeastSquareSLIM
 Sparse Linear Methods (SLIM) for item prediction (ranking) optimized for the elastic net loss. More...
class  MF
 Abstract class for matrix factorization based item predictors. More...
class  MostPopular
 Most-popular item recommender. More...
class  MostPopularByAttributes
 Recommend most popular items by attribute. More...
class  MultiCoreBPRMF
 Matrix factorization for BPR on multiple cores. More...
class  Random
 Random item recommender for use as experimental baseline. More...
class  SLIM
 Abstract class for SLIM based item predictors proposed by Ning and Karypis. More...
class  SoftMarginRankingMF
 Matrix factorization model for item prediction optimized for a soft margin (hinge) ranking loss, using stochastic gradient descent (as in BPR-MF). More...
class  UserAttributeKNN
 k-nearest neighbor (kNN) user-based collaborative filtering using the correlation of the user attibutes More...
class  UserKNN
 k-nearest neighbor user-based collaborative filtering More...
class  WeightedBPRMF
 Weigthed BPR-MF with frequency-adjusted sampling. More...
class  WRMF
 Weighted matrix factorization method proposed by Hu et al. and Pan et al. More...
class  Zero
 Constant item recommender for use as experimental baseline. Always predicts a score of zero. More...

Detailed Description

This namespace contains item recommenders and some helper classes for item recommendation.