Pavel Kordík
Mar 30, 2016 · 3 min read

Artificial Intelligence in the Cloud

At Recombee, we “think big”, and prefer making big leaps in technology over taking small steps. Our team has been involved in data science and artificial intelligence research for many years. Beginning in 2012, we began to capitalize our knowledge and experience, developing products which help a wide range of companies to improve their business.

Our currently most successful product is a universal “recommender engine”, controlled and maintained by advanced artificial intelligence. In short, we developed special query language that makes real time recommendation requests of our customers very powerful — matching exactly their business needs. A website running our system will literally get to know a user’s preferences over the course of time.

In real world use, our recommender systems can be used in e-commerce to generate personalized recommendations for individual users helping customers to find relevant products. E-shop owners can increase their direct and indirect income and loyalty of their customers by only showing them products which are preferential. In the same way, our systems can recommend jobs, movies or cultural events. Our solution is general, scalable, easy to customize and powered by artificial intelligence.

Artificial intelligence is capable of handling and automating extremely diffucult tasks, normally being performed by people. The complexity of data science behind predictive models normally requires highly qualified experts with invention. However, even in this area there are many tasks that can be automated using the artificial intelligence. For example, selection and parameterizations of appropriate algorithms for recommendation. Human experts perform this task inefficiently, because experiments evaluating predictive power of algorithms on the given data are time consuming and there are infinite number of possibilities how these algorithms can be assembled and parameterized.

Artificial intelligence is capable of maintaining and improving thousands of algorithms in parallel for our customers, so we don’t need to employ army of data scientists.

Thanks to scalable cloud infrastructure and AI, we are able to adjust our system for new customer within few minutes. This is very cost efficient and our products are affordable even for smaller companies such as e-shops that would not be able to build and maintain recommender system themselves.

Moreover, according to AB test results of our larger customers that developed recommender systems or predictive models internally, our algorithms and artificial intelligence often outperform their solutions.

This is mainly due to the fact that they run outdated or biased models and fail to maintain them as the environment and data change. Maintaining models is cumbersome, routine work that most of data scientists do not enjoy.

We’re convinced that another industrial revolution has just begun.

Artificial intelligence helps people with solving tasks requiring creativity and invention. Some tasks it can do even better, utilizing large amount of data from different sources and increasing computational power of cloud infrastructures. There is a danger that half of the jobs as we know them could disappear within a few years — or more precisely, be transformed to new positions and opportunities.

This is a challenge for most of us. At Recombee, we have already found the solution with how to cooperate with the AI, and we think we’re pretty good as a team.

Recombee is also pushing forward the limits of existing systems and improving artificial intelligence algorithms. In fact, two members of our team have their papers accepted for publication at World Congress of Computational Intelligence .

Our goal is to bring you solutions that can significantly and substantially improve your business. Let us know how we can help you at

Recombee blog

We develop global recommendation service and share our…

Recombee blog

We develop global recommendation service and share our insighst here.

Pavel Kordík

Written by

@FIT_CTU, @DataLab_CTU, @recombee,

Recombee blog

We develop global recommendation service and share our insighst here.