Zen (Russian: Дзéн, romanized: Dzen) is a personal recommender system that uses machine learning technology.
[7] The selection of content is based on the analysis of browsing history, user-specified preferences, location, time of day and other factors.
[19][20] The technology that underlies Zen was adapted by Yandex and CERN for use in the Large Hadron Collider.
[21][22] In 2017, Yandex announced the launch of a platform that allows companies and independent authors to publish media content (articles, photos, videos) directly to Zen.
[32] In May 2020, bloggers on the platform had the opportunity to place widgets with goods from Yandex Market: at that time, such social commerce was implemented only in articles.
[34] At the first stage of the launch of the short video feed Yandex allocated 50 million rubles to reward bloggers.
In 1997, Yandex began research into natural language processing, machine learning and recommendation systems.
[35] In 2009, the proprietary machine learning algorithm MatrixNet was developed by Yandex, becoming one of the key components that Zen functions on.
[9][39] In the following months, other types of content were added to Zen, such as image galleries, articles, blogs, forums, videos from YouTube, etc.