 AttributeData | Class that offers static methods to read (binary) attribute data into IBooleanMatrix objects |
 AUC | Area under the ROC curve (AUC) of a list of ranked items |
 CombinedList< T > | Combines two List objects |
 Constants | Static class containing constants used by the MyMediaLite Input/Output routines |
 DataReaderExtensions | Extension methods for IDataReader objects |
 EntityMappingExtensions | I/O routines for classes implementing the IEntityMapping interface |
 EvaluationResults | Class for representing evaluation results |
  ItemRecommendationEvaluationResults | Item recommendation evaluation results |
  RatingPredictionEvaluationResults | Rating prediction evaluation results |
 Extensions | Extension methods for correlation matrices |
 Extensions | Extension methods for dataset statistics |
 Extensions | Class that contains static methods for rating prediction |
 Extensions | Helper class with utility methods for handling recommenders |
 Extensions | Class that contains static methods for item prediction |
 FileSerializer | Static class for serializing objects to binary files |
 FileSystem | File-system related helper functions |
 FoldIn | Fold-in evaluation |
 FoldInRatingPredictorExtensions | Extension methods for IFoldInRatingPredictor |
 GridSearch | Grid search for finding suitable hyperparameters |
 Handlers | Class containing handler functions, e.g. exception handlers |
 IDataSet | Interface for different kinds of collaborative filtering data sets |
  DataSet | Abstract dataset class that implements some common functions |
   PosOnlyFeedback< T > | Data structure for implicit, positive-only user feedback |
   Ratings | Data structure for storing ratings |
    CombinedRatings | Combine two IRatings objects |
    RatingsProxy | Data structure that allows access to selected entries of a rating data structure |
    StaticRatings | Array-based storage for rating data. |
     StaticByteRatings | Array-based storage for rating data. |
    TimedRatings | Data structure for storing ratings with time information |
     TimedRatingsProxy | Data structure that allows access to selected entries of a timed rating data structure |
  IPosOnlyFeedback | Interface for implicit, positive-only user feedback |
   PosOnlyFeedback< T > | Data structure for implicit, positive-only user feedback |
  IRatings | Interface for rating datasets |
   ITimedRatings | Interface for rating datasets with time information |
    TimedRatings | Data structure for storing ratings with time information |
   Ratings | Data structure for storing ratings |
  ITimedDataSet | interface for data sets with time information |
   ITimedRatings | Interface for rating datasets with time information |
 IHyperParameterSearch | Interface for classes that perform hyper-parameter search |
 IIncrementalRecommender | Interface for recommenders that support incremental model updates. |
  IIncrementalItemRecommender | Interface for item recommenders |
   IncrementalItemRecommender | Base class for item recommenders that support incremental updates |
    KNN | Base class for item recommenders that use some kind of k-nearest neighbors (kNN) model |
     ItemKNN | k-nearest neighbor (kNN) item-based collaborative filtering |
      ItemAttributeKNN | k-nearest neighbor (kNN) item-based collaborative filtering using the correlation of the item attibutes |
     UserKNN | k-nearest neighbor user-based collaborative filtering |
      UserAttributeKNN | k-nearest neighbor (kNN) user-based collaborative filtering using the correlation of the user attibutes |
    MF | Abstract class for matrix factorization based item predictors |
     BPRMF | Matrix factorization model for item prediction (ranking) optimized for BPR |
      MultiCoreBPRMF | Matrix factorization for BPR on multiple cores |
      SoftMarginRankingMF | Matrix factorization model for item prediction optimized for a soft margin (hinge) ranking loss, using stochastic gradient descent (as in BPR-MF). |
      WeightedBPRMF | Weigthed BPR-MF with frequency-adjusted sampling |
     WRMF | Weighted matrix factorization method proposed by Hu et al. and Pan et al. |
    MostPopular | Most-popular item recommender |
    SLIM | Abstract class for SLIM based item predictors proposed by Ning and Karypis |
     BPRSLIM | Sparse Linear Methods (SLIM) for item prediction (ranking) optimized for BPR-Opt optimization criterion |
     LeastSquareSLIM | Sparse Linear Methods (SLIM) for item prediction (ranking) optimized for the elastic net loss |
  IIncrementalRatingPredictor | Interface for rating predictors which support incremental training |
   IncrementalRatingPredictor | Base class for rating predictors that support incremental training |
    Constant | Uses a constant rating value for prediction |
    EntityAverage | Abstract class that uses an average (by entity) rating value for predictions |
     ItemAverage | Uses the average rating value of an item for prediction |
     UserAverage | Uses the average rating value of a user for predictions |
    GlobalAverage | Uses the average rating value over all ratings for prediction |
    KNN | Base class for rating predictors that use some kind of kNN |
     ItemKNN | Weighted item-based kNN |
      ItemAttributeKNN | Attribute-aware weighted item-based kNN recommender |
     UserKNN | Weighted user-based kNN |
      UserAttributeKNN | Weighted kNN recommender based on user attributes |
    MatrixFactorization | Simple matrix factorization class, learning is performed by stochastic gradient descent (SGD) |
     BiasedMatrixFactorization | Matrix factorization with explicit user and item bias, learning is performed by stochastic gradient descent |
      SigmoidCombinedAsymmetricFactorModel | Asymmetric factor model which represents items in terms of the users that rated them, and users in terms of the items they rated |
      SigmoidItemAsymmetricFactorModel | Asymmetric factor model |
      SigmoidUserAsymmetricFactorModel | Asymmetric factor model which represents items in terms of the users that rated them |
      SocialMF | Social-network-aware matrix factorization |
     SVDPlusPlus | SVD++: Matrix factorization that also takes into account what users have rated |
      GSVDPlusPlus | Item Attribute Aware SVD++: Matrix factorization that also takes into account what users have rated and its attributes. |
      SigmoidSVDPlusPlus | SVD++: Matrix factorization that also takes into account what users have rated; variant that uses a sigmoid function |
    NaiveBayes | Attribute-aware rating predictor using Naive Bayes |
    Random | Uses a random rating value for prediction |
    UserItemBaseline | Baseline method for rating prediction |
 IItemSimilarityProvider | Interface for classes that provide item similarities |
  ItemKNN | k-nearest neighbor (kNN) item-based collaborative filtering |
  ItemKNN | Weighted item-based kNN |
 IIterativeModel | Interface representing iteratively trained models |
  BPRLinear | Linear model optimized for BPR |
  MF | Abstract class for matrix factorization based item predictors |
  SLIM | Abstract class for SLIM based item predictors proposed by Ning and Karypis |
  CoClustering | Co-clustering for rating prediction |
  FactorWiseMatrixFactorization | Matrix factorization with factor-wise learning |
  LatentFeatureLogLinearModel | Latent-feature log linear model |
  MatrixFactorization | Simple matrix factorization class, learning is performed by stochastic gradient descent (SGD) |
  TimeAwareBaseline | Time-aware bias model |
   TimeAwareBaselineWithFrequencies | Time-aware bias model with frequencies |
  UserItemBaseline | Baseline method for rating prediction |
 IMapping | Interface to map external entity IDs to internal ones to ensure that there are no gaps in the numbering |
  IdentityMapping | Identity mapping for entity IDs: Every original ID is mapped to itself |
  Mapping | Class to map external entity IDs to internal ones to ensure that there are no gaps in the numbering |
 IMatrix< T > | Generic interface for matrix data types |
  ICorrelationMatrix | Interface representing correlation and similarity matrices |
   AsymmetricCorrelationMatrix | Class for computing and storing correlations and similarities |
    BinaryDataAsymmetricCorrelationMatrix | Class with commoin routines for asymmetric correlations that are learned from binary data |
     BidirectionalConditionalProbability | Class for storing and computing 'bi-directional' conditional probabilities |
     ConditionalProbability | Class for storing and computing conditional probabilities |
   IBinaryDataCorrelationMatrix | CorrelationMatrix that computes correlations over binary data |
    BinaryDataAsymmetricCorrelationMatrix | Class with commoin routines for asymmetric correlations that are learned from binary data |
    BinaryDataSymmetricCorrelationMatrix | Class with common routines for symmetric correlations that are learned from binary data |
     BinaryCosine | Class for storing cosine similarities |
     Cooccurrence | Class for storing and computing the co-counts |
     Jaccard | Class for storing and computing the Jaccard index (Tanimoto coefficient) |
   IRatingCorrelationMatrix | CorrelationMatrix that computes correlations over rating data |
    Pearson | Shrunk Pearson correlation for rating data |
   SymmetricCorrelationMatrix | Class for computing and storing correlations and similarities |
    BinaryDataSymmetricCorrelationMatrix | Class with common routines for symmetric correlations that are learned from binary data |
    Pearson | Shrunk Pearson correlation for rating data |
  IBooleanMatrix | Interface for boolean matrices |
   SparseBooleanMatrix | Sparse representation of a boolean matrix, using HashSets |
  Matrix< T > | Class for storing dense matrices |
  SparseMatrix< T > | Class for storing sparse matrices |
   AsymmetricCorrelationMatrix | Class for computing and storing correlations and similarities |
   SymmetricSparseMatrix< T > | a symmetric sparse matrix; consumes less memory |
    SymmetricCorrelationMatrix | Class for computing and storing correlations and similarities |
    SkewSymmetricSparseMatrix | a skew symmetric (anti-symmetric) sparse matrix; consumes less memory |
   SymmetricSparseMatrix-g< float > | |
  SymmetricMatrix< T > | Class for storing dense matrices |
 IMatrix-g< bool > | |
 IMatrix-g< float > | |
 INeedsMappings | Interface for classes that need user and item ID mappings, e.g. for recommenders that read data from external sources and thus need to know which IDs are used externally. |
  ExternalItemRecommender | Uses externally computed predictions |
  ExternalRatingPredictor | Uses externally computed predictions |
 IRecommender | Generic interface for simple recommenders |
  Ensemble | Abtract class for combining several prediction methods |
   WeightedEnsemble | Combining several predictors with a weighted ensemble |
  IItemAttributeAwareRecommender | Interface for recommenders that take binary item attributes into account |
   BPRLinear | Linear model optimized for BPR |
   ItemAttributeKNN | k-nearest neighbor (kNN) item-based collaborative filtering using the correlation of the item attibutes |
   MostPopularByAttributes | Recommend most popular items by attribute |
   GSVDPlusPlus | Item Attribute Aware SVD++: Matrix factorization that also takes into account what users have rated and its attributes. |
   ItemAttributeKNN | Attribute-aware weighted item-based kNN recommender |
   NaiveBayes | Attribute-aware rating predictor using Naive Bayes |
  IItemRelationAwareRecommender | Interface for recommenders that take a binary relation over items into account |
  IFoldInItemRecommender | Item recommender that allows folding in new users |
   BPRMF | Matrix factorization model for item prediction (ranking) optimized for BPR |
   UserKNN | k-nearest neighbor user-based collaborative filtering |
  IUserAttributeAwareRecommender | Interface for recommenderss that take binary user attributes into account |
   UserAttributeKNN | k-nearest neighbor (kNN) user-based collaborative filtering using the correlation of the user attibutes |
   UserAttributeKNN | Weighted kNN recommender based on user attributes |
  IUserRelationAwareRecommender | Interface for recommenders that take a binary relation over users into account |
   SocialMF | Social-network-aware matrix factorization |
  IRatingPredictor | Interface for rating predictors |
   IFoldInRatingPredictor | Rating predictor that allows folding in new users |
    ItemKNN | Weighted item-based kNN |
    MatrixFactorization | Simple matrix factorization class, learning is performed by stochastic gradient descent (SGD) |
    UserAverage | Uses the average rating value of a user for predictions |
    UserKNN | Weighted user-based kNN |
   IIncrementalRatingPredictor | Interface for rating predictors which support incremental training |
   ITimeAwareRatingPredictor | Interface for time-aware rating predictors |
    TimeAwareRatingPredictor | Abstract class for time-aware rating predictors |
     TimeAwareBaseline | Time-aware bias model |
   ITransductiveRatingPredictor | Rating predictor that knows beforehand what it will have to rate |
    SigmoidCombinedAsymmetricFactorModel | Asymmetric factor model which represents items in terms of the users that rated them, and users in terms of the items they rated |
    SigmoidItemAsymmetricFactorModel | Asymmetric factor model |
    SigmoidSVDPlusPlus | SVD++: Matrix factorization that also takes into account what users have rated; variant that uses a sigmoid function |
    SigmoidUserAsymmetricFactorModel | Asymmetric factor model which represents items in terms of the users that rated them |
    SVDPlusPlus | SVD++: Matrix factorization that also takes into account what users have rated |
   RatingPredictor | Abstract class for rating predictors that keep the rating data in memory for training (and possibly prediction) |
    BiPolarSlopeOne | Bi-polar frequency-weighted Slope-One rating prediction |
    CoClustering | Co-clustering for rating prediction |
    ExternalRatingPredictor | Uses externally computed predictions |
    FactorWiseMatrixFactorization | Matrix factorization with factor-wise learning |
    IncrementalRatingPredictor | Base class for rating predictors that support incremental training |
    LatentFeatureLogLinearModel | Latent-feature log linear model |
    SlopeOne | Frequency-weighted Slope-One rating prediction |
    TimeAwareRatingPredictor | Abstract class for time-aware rating predictors |
  Recommender | Abstract recommender class implementing default behaviors |
   ItemRecommender | Abstract item recommender class that loads the (positive-only implicit feedback) training data into memory and provides flexible access to it. |
    BPRLinear | Linear model optimized for BPR |
    ExternalItemRecommender | Uses externally computed predictions |
    IncrementalItemRecommender | Base class for item recommenders that support incremental updates |
    MostPopularByAttributes | Recommend most popular items by attribute |
    Random | Random item recommender for use as experimental baseline |
    Zero | Constant item recommender for use as experimental baseline. Always predicts a score of zero |
   RatingPredictor | Abstract class for rating predictors that keep the rating data in memory for training (and possibly prediction) |
 ISplit< T > | generic dataset splitter interface |
  PosOnlyFeedbackCrossValidationSplit< T > | K-fold cross-validation split for item prediction from implicit feedback |
  PosOnlyFeedbackSimpleSplit< T > | simple split for item prediction from implicit feedback |
  RatingCrossValidationSplit | k-fold cross-validation split for rating prediction |
  RatingsChronologicalSplit | chronological split for rating prediction |
  RatingsPerUserChronologicalSplit | per-user chronological split for rating prediction |
  RatingsSimpleSplit | simple split for rating prediction |
 ISplit-g< IPosOnlyFeedback > | |
 ISplit-g< IRatings > | |
 ISplit-g< ITimedRatings > | |
 ItemData | Class that contains static methods for reading in implicit feedback data for ItemRecommender |
 ItemDataRatingThreshold | Class that contains static methods for reading in implicit feedback data for ItemRecommender, derived from rating data |
 Items | Routines for reading in the item taxonomy of the KDD Cup 2011 data |
 Items | Evaluation class for item recommendation |
 ItemsCrossValidation | Cross-validation for item recommendation |
 ItemsOnline | Online evaluation for rankings of items |
 ITransductiveItemRecommender | Interface for item recommenders that take into account some test data for training |
 IUserSimilarityProvider | Interface for classes that provide user similarities |
  UserKNN | k-nearest neighbor user-based collaborative filtering |
  UserKNN | Weighted user-based kNN |
 KDDCupItems | Represents KDD Cup 2011 items like album, track, artist, or genre |
 ListProxy< T > | Proxy class that allows access to selected elements of an underlying list data structure |
 LogisticLoss | Utility functions for the logistic loss |
 MAE | Utility functions for the mean absolute error |
 MatrixExtensions | Utilities to work with matrices |
 MatrixExtensions | Utilities to work with matrices |
 Memory | Memory-related tools |
 Model | Class containing static routines for reading and writing recommender models |
 MovieLensRatingData | Class that offers static methods for reading in MovieLens 1M and 10M rating data |
 MultiCore | Utility routines for multi-core algorithms |
 NDCG | Normalized discounted cumulative gain (NDCG) of a list of ranked items |
 NelderMead | Nealder-Mead algorithm for finding suitable hyperparameters |
 Overlap | Class containing routines for computing overlaps |
 PrecisionAndRecall | Precision and recall at different positions in the list |
 Random | Random number generator singleton class |
 RatingBasedRankingCrossValidation | Cross-validation for rating-based ranking |
 RatingData | Class that offers methods for reading in rating data |
 Ratings | Class that offers static methods for reading in rating data from the KDD Cup 2011 files |
 Ratings | Evaluation class for rating prediction |
 RatingScale | Class containing information about the rating scale of a data set: valid rating values, minimum/maximum rating. |
 RatingsCrossValidation | Cross-validation for rating prediction |
 RatingsOnline | Online evaluation for rating prediction |
 ReciprocalRank | The reciprocal rank of a list of ranked items |
 RecommenderParameters | Class for key-value pair string processing |
 RelationData | Class that offers static methods to read (binary) relation over entities into IBooleanMatrix objects |
 RMSE | Utility functions for the root mean square error (RMSE) |
 SequentialDiversification | Sequential diversification |
 SparseMatrixExtensions | Utilities to work with matrices |
 StaticRatingData | Class that offers methods for reading in static rating data |
 TimedRatingData | Class that offers methods for reading in rating data with time information |
 Track2Items | Class that offers static methods for reading in test data from the KDD Cup 2011 files |
 TransductiveRatingPredictorExtensions | Helper methods for ITransductiveRatingPredictor |
 Utils | Class containing utility functions |
 VectorExtensions | Extensions for vector-like data |
 VectorExtensions | Extensions for vector-like data |
 Wrap | Static methods to wrap around other code. |