The first neural network-based service that recommends a particular film or series for viewing has started operating in Russia. The development of the MTS and KION Big Data Center includes all films and series that have ever been presented on the film service. The selection includes even those film works that are no longer shown in Russia.
We decided to create a new tool that will help users choose the most suitable films and series for themselves — for example, if you want to watch something new, or you need to choose one film for a company of several people. The Explore KION neural network allows you to do this, and its main value for us as a service is that it saves users time choosing a film.
Explore KION is based on which film works the user liked.
After selection, the neural network, based on the user's current preferences, will select a list of relevant pictures that can be viewed on KION.
Explore KION works with two levels of algorithm. The candidate selection model selects films and series that the user may like based on what he has chosen.
Then the films and series selected at the first level and the history of interactions with cards from the current session are included in the ranking model.
The algorithm will also work when you need to choose a film for a company of viewers with different interests.