The best technology conference on the planet 6. - 8. November 2018! Follow our LinkedIn for more info.
Frequently Asked Questions
Explore the Most Asked Questions
Our standard pricing is purely usage-based. All plans are pay-as-go plan - you never pay more than you use.
The Standard account starts at $99/mth -- you'll get separate instance on our enterprise infrastructure with high availability guarantees, and also API integration support.
The price list consists of two components: active users and number of recommendation requests. When properly integrated, number of active users is roughly equivalent to number of Users you can find in Google Analytics for given period of 1 month. For the Recommendation requests, only the number of invoked requests counts, no matter the number of returned items per request.
Yes. We maintain a priority list of new features based on customer suggestions. We are quite strong in research, innovations and inventing new functionality is our passion. Check out our articles on Recombee blog to find out more about recently launched inverse recommendations and other features.
Recommender system is a technology that is deployed in the environment where items (products, movies, events, articles)are to be recommended to users (customers, visitors, app users, readers) or the opposite. Typically, there are many items and many users present in the environment making the problem hard and expensive to solve.
Check our blog post explaining the topic in further detail here.
We never share data with third parties, neither we share data between individual clients (there is no cross-database data enrichment).
I want to deploy Recombee at many websites at once - do you provide an API for automated managing (creating/deleting) of databases?
Yes, we do. Please contact us at email@example.com and we will give you all the necessary information.
You can do it easily using our innovative query language ReQL. Each recommendation request has parameter filter, where you can specify a condition based on the values of the properties. For example, if you have specified a string item property called category and want get only books, the filter is ‘category’==”books”.
We use an ensemble of collaborative filtering (matrix factorization, nearest neighbors …) algorithms, which work on the interactions (views, purchases…), and content-based algorithms, which work on the item properties (titles, descriptions…).
The decision about used algorithms is automated - if there is not a lot of interactions (for example in case of new (cold start) items), content based algorithms are chosen. In case of sufficient number of interactions collaborative filtering algorithms are preferred as they in most cases give the best results.