Search engine is the core Yandex product. Its goal is to provide a user with the answer to her search query. The search engine uses Yandex’s proprietary algorithms to provide relevant structured results presented in an editorially neutral and user-friendly manner. In October 2010 Yandex’s share of Russian search market was 64.6%.
Yandex’s search technology provides local search results in more than 1,250 Russian cities; also shown are the local results for users in Belarus, Kazakhstan and Ukraine. So called “parallel” search presents on a single page the results from both main web index and specialized information resources, including news, shopping, blogs, images and videos. A user can access Yandex’s search engine through personal computers, mobile phones, tablets, and navigation and other digital devices.
Since 2009 Yandex’s search engine relies on MatrixNet, a new method of machine learning. MatrixNet allows generate a very long and complex ranking formula, which considers a multitude of various factors and their combinations. It builds a formula based on tens of thousands of factors, which significantly increases the relevance of search results. Another search technology, Spectrum, fights ambiguous queries, delivering different results based on users’ intents.
In May 2010 Yandex added foreign content to its index and launched Yandex.com, the experimental site for testing new search algorithms.