The Duine Recommender Framework

Your cherry picking tool.....

Too many TV channels! How can I find the programs I like? What books in our city library should I read? Can you find me some nice friends in Hyves and Facebook? Or maybe you need a defriending assistant: I have 2000 friends in my networks, which ones should I drop? I have too many RSS feeds in my RSS reader, I only want to see the interesting items in those feeds!

Are you a software developer that is interested in building applications that solve this kind of issues for their users? If so, you should take a look at the open source Duine Recommender Framework (http://duineframework.org) that we have developed here at the Telematica Instituut. It is a software module that calculates how interesting information items are for a user.
It uses a mixture of clever algorithms as well as user profiles to predict the level of interest. And..... it can learn: users can provide feedback (ratings) that will be stored in the profiles and used by the algorithms to get even better predictions.

The Duine Recommender can be used in any application domain and can be connected to any type of content. The persistency packages are Hibernate based, so you can store user profiles in any relational database product without any recoding.

The Duine Recommender was developed in java, and designed with the application developer in mind. The core client interface is extremely simple. The harder part is the configuration, but the framework comes with a default configuration that works quite well out-of-the-box. And ..... if you use Maven, our libraries are in the global Maven repositories, so add the dependency in your pom.xml and you're application is ready for cherry picking.

Got interested? Want to download? Take a look at http://duineframework.org. You will find extensive documentation, a forum and contact info as well.