The MyMedia toolkit is an extensible software framework for multimedia recommendation, incorporating cutting edge recommender algorithms and metadata enrichment. This C# developed research project makes it easier to study, develop and deploy personalization
Users and implementers of multimedia today face a common problem: how to deal with the “crisis of choice” that exists when very many different forms of multimedia are presented to users. In such circumstances search is not a complete solution, recommendation
can improve the user experience. However there are few recommender system solutions that are sufficiently versatile.
The MyMedia software toolkit is the outcome of an international collaboration to develop an extensible software framework for multimedia recommendation, incorporating cutting edge recommender algorithms, metadata enrichment, and software design. It will be
tested in field trials under realistic conditions while being made available to the research community. This software provides a structured approach to personalization, as well as reusable reference implementations of popular recommendation and enrichment
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 prediction from implicit feedback (e.g. from clicks or purchase actions).
MyMediaLite binaries, source code and documentation can be downloaded from:
Project Home Page
Related EC Projects
The MyMedia toolkit has benefited from the contributions of many people involved in the MyMedia project through its partners: EMIC; BT; the BBC; the Technical University of Eindhoven; the University of Hildesheim, Microgenesis and Novay (formerly the Telematica
Instituut). The MyMedia software toolkit has been developed as part of the MyMedia project funded through the EU Framework 7 Programme Networked Media initiative (Project Number IST-2008-215006).