Description:

MyMediaLite is a lightweight, multi-purpose library of recommender system algorithms.

It addresses the two most common scenarios in collaborative filtering:

• rating prediction (e.g. on a scale of 1 to 5 stars), and
• item recommendation from positive-only feedback (e.g. from clicks or purchase actions).

MyMediaLite gives you a choice of many recommendation methods:

• dozens of different recommenders
• methods can use collaborative and attribute/content data

MyMediaLite is ready to use:

• MyMediaLite includes evaluation routines for rating prediction and item prediction; it can measure MAE, NMAE, RMSE, CBD, AUC, prec@N, MAP, NDCG, MRR.
• It also comes with command line tools for both recommendation tasks that read a simple text-based files.

MyMediaLite is compact: The core library has a size of about 150KB.

Portability: Written in C#, for the .NET platform; runs on every architecture supported by Mono: Linux, Windows, Mac OS X.

Freedom: MyMediaLite is free software/open source software. It can be used, modified, and distributed under the terms of the GNU General Public License (GPL).

Additional features:

• Serialization: save and reload recommender models
• Real-time incremental updates for many recommenders
• multi-core support

Changes to previous version:

Most prominenty, we have several new rating predictors, all of them variants of asymmetric factor models (AFMs). The new item recommender MostPopularByItemAttributes generalizes an idea presented by the organizers of the Million Song Database Challenge. We now have 27 different rating predictors and 18 different item recommenders in MyMediaLite.

Existing recommender have received significant improvements:

• WRMF: support out-of-the-box multi-core learning (#233)
• BiasedMatrixFactorization: 'naive' parallelization
• (Sigmoid)SVDPlusPlus, SigmoidItemAsymmetricFactorModel: take the ratings that have to be predicted into account (transductive learning)

Evaluation improvements:

• MyMediaLite.Extensions: parameter n (number of top-n predictions) for PredictItems() and ScoreItems() methods
• rating prediction: detailed evaluation of cold-start events
• remove ItemsFiltered class

Scripts:

• add scripts for creating submissions, evaluation, and blending for the Million Song Dataset Challenge on Kaggle
• add script for user-stratified crossvalidation
• import_dataset.pl: more flexible ID mapping file format

Testing

• NUnit tests now also run from the command line

More details can be found in the Changes file: https://github.com/zenogantner/MyMediaLite/blob/master/doc/Changes

BibTeX Entry: Download

Corresponding Paper BibTeX Entry: Download

Supported Operating Systems: Linux, Windows, Solaris, Mac Os X

Data Formats: Csv, Tab Separated, Sql

Tags: Gradient Based Learning, Large Scale Learning, Algorithms, Data Mining, Evaluation, Supervised Learning, Collaborative Filtering, Matrix Factorization, Recommender Systems, Knn, Library, Dotnet, Mono

Archive: download here

Comments

No one has posted any comments yet. Perhaps you'd like to be the first?

Leave a comment

You must be logged in to post comments.