If you are interested in the rocket science behind Gravity R&D's recommendation platform, you have come to the right place. Feel free to contact us, if you have further questions.
Recommendation systems are a type of information filtering systems that recommend products available in e-shops, entertainment items (books music, videos, Video on Demand, books, news, images, events etc.) or people (e.g. on dating sites) that are likely to be of interest to the user.
Gravity’s recommendation system automatically learns and analyses the browsing / shopping behavior of the user on a given website or platform. Then based on this information and based on several other similar profiles the recommendation system shows items that are fit the taste of the given user.
Recommender systems are new generation of information organization tools that help your information-overloaded users find relevant content.
These platforms also enable you, a content provider to offer personalized services for each and every user according to her taste and interest. The question is always: how can recommender systems characterize the preferences of each individual user? There are two main approaches to do that:
We have a fine group of PhD's who enjoy pushing the limits of mining big data. Not only are they good in practice, our researchers also contribute to scientific publications and conferences. Meet the team that is responsible for developing the heart of Gravity's recommendation technology.
Our data mining team publishes actively in the field of recommender systems. Here you can find details for some selected papers along with a brief description on the paper content.
The Netflix Prize was the most reputed open competition for the best collaborative filtering algorithms that could predict user ratings for films based on previous ratings. Gravity's team consistently performed among the top 10, and finished (tied) with the highest performance in the competition. The competition was announced in late 2006, after the significant benefits of quality and personalized recommendations became apparent.