Yandex Updated Search Using CS YATI Neural Network

Yandex has improved search using the CS YATI neural network, a new model trained on documents for IT specialists and assessments of programming experts.

Search results for developers and ML-specialists have become better, and query navigation has become more convenient.

Working principle of CS YATI

The new CS YATI model takes into account 1.5 times more information from the page than its previous version – YATI.

Evaluation of the quality and relevance of the document to the query – the updated transformer neural network analyzed many search queries and sites that are shown for queries related to programming. This helps her better evaluate the quality and relevance of the document to the query.

Skilled Programmer Click Prediction – By running through terabytes of programming documents and expert search history, CS YATI has learned to predict the clicks of skilled programmers to generate the most relevant response.

Alexey Gusakov, Head of Machine Intelligence and Research Department at Yandex was quoted in the Yandex press release stating:

It is known that the lion’s share of programming requests are requests in English. CS YATI was trained mainly on English-language sources. We have not only improved the search for programmers: in the process we have also improved the search for English-language sources.

Dan Taylor
Dan Taylor is an experienced SEO consultant and has worked with brands and companies on optimizing for Russia (and Yandex) for a number of years. Winner of the inaugural 2018 TechSEO Boost competition, webmaster at and Sloth.Cloud, and founder of