InBeat - Interest Beat

Interest Beat is a service for recommendation of content. InBeat was designed with emphasis on versatility, scalability and extensibility. The core contains the General Analytics INterceptor module, which collects and aggregates user interactions, the Preference Learning module and the Recommender System module.

Try demo or watch screencast!

New Jaroslav Kuchař, Tomáš Kliegr, InBeat: JavaScript recommender system supporting sensor input and linked data, Knowledge-Based Systems, Volume 135, 1 November 2017, Pages 40-43, ISSN 0950-7051, https://doi.org/10.1016/j.knosys.2017.07.026.

New The InBeat (inbeat.eu) recommender developed with support from LinkedTV received a runner-up prize in the News Recommender Challenge (https://sites.google.com/site/newsrec2013/challenge), which focused on recommending news articles in real-time. InBeat came second out of 17 participating systems. During the three weeks of the contest, it handled over 20 million recommendation requests. The News Recommender Challenge is organized in conjunction with the ACM Conference on Recommender Systems (http://recsys.acm.org/recsys13/). InBeat will be presented (together with the LinkedTV-supported GAIN platform) also at the main conference (http://recsys.acm.org/recsys13/demos/).

GAIN

GAIN (General Analytics INterceptor) collects and aggregates user interactions.

More Info

Preference Learning

This component is responsible for learning the preferences and wraps the underlying learning stack.

More Info

Recommeder System

Provides recommendations of content based on different algorithms.

More Info

If you are already using InBeat then please cite our work!