Today we are going to talk about how the Yandex algorithm has evolv over the last few years and its latest key updates, which have mark a before and after in how the search engine analyzes search queries and returns results bas on the nes of users. Palekh (2016), Korolyov (2017), and Androma (2018) rely on artificial intelligence from neural networks to better understand the user’s search intent , going a step beyond simply analyzing keywords and focusing more on understanding their meaning .
Despite Google’s monopoly in the vast majority of countries around the world
Yandex’s market share in Russia continues to prominate over the Californian giant , and, given its unstoppable expansion and technological development, it does not seem that the scenario will change in the coming years.
According to SEJournal , in 2019 , 52% of Russian-speaking users still prefer Yandex, compar to 46% of Internet users who opt for Google.
In the same interview given to SEJournal by the Yandex team, we also found out that the penetration of mobile searches and voice searches in the Russian search engine is increasing, being approximately 56% and 20% of the total, respectively.
Palekh
Since its introduction in November 2016 with Palekh
Yandex has been further refining and fine-tuning its neural network-bas algorithm to respond to more complex search intentions and queries with the help of machine learning , with a special emphasis on long-tail queries . In its first launch, it had more limit capabilities, as it was only able to analyze the titles of web pages, but not the content in its entirety, in addition to being considerably slower than its successor (which we will discuss shortly), processing around 40% of the requests made to the search engine out of the 280 million daily.
The technology of “ semantic vectors ” us by Palekh is bas on distributional semantic
As they explain on their blog (in Russian) , words from billions You get the correctphone number list contact lists to your merchandise and carona sufferas our information are 100% accurate. Our phone number list database is in the climax of success for your business. Our databases aggregate with the data middle east mobile number list advertiser collect from permission sites(best database quality or quantity by using it, you can earn leads) to generate more interest in your business and boost sales. of queries are convert into numbers, or rather groups of 300 numbers each. These are distribut across a 300-dimensional space, where each document has its own vector. If the numbers corresponding to a query are close to the numbers corresponding to a document in that space, the result is consider relevant. The closer they are to each other, the more relevant the page return by the search engine.
The small town of Palekh in Russia serv as inspiration for naming the algorithm after its peculiar shield featuring a firebird ,
whose most distinctive feature is its long tail
Within long-tail keywords, Yandex distinguishes several categories, ranging from more to less specific. The most relevant queries and results will not always have words in common, which certainly makes the job more difficult for the search engine. For example:
Queries where a person cannot remember the name of the film they have recently seen, but a very specific scene from it has stuck in their mind: “film about a man who plant potatoes on another planet” > Mars (The Martian).
People, often children, who do not yet fully understand how to address a search engine and speak to it as if it were an entity in itself: “yandex, please recommend me some interesting games about fairies for the tablet” > Their search intent could probably be summ up as a page that recommends games with a fantasy component for the iOS or Android platforms.
And this is where the ne arises to teach
The algorithm to be able to respond to the most natural and “human” user searches.
Yandex offers us the following graphical representation of the operation of the Palekh algorithm, in two dimensions for us mere mortals:
Korolyov
Almost a year later, in August 2017, the next major update to Yandex’s intelligent algorithm was releas: Korolyov.
Korolyov is bas on Palekh, but it is even more powerful
Whereas the previous update only look at the title tag to find matches between the search term enter by a user and the results, Korolyov reads and analyzes the entire content of the page , to return results that are much more closely relat to the search intent . Not only that, but its capacity to process documents in real time is multipli by a thousand. In addition, since it is a system bas on artificial intelligence, its neural network learns more and more, thanks to a thorough analysis of user behavior in response to the results offer. It compares the current query with others that have l a user to the same content, or looks at the time someone has spent on a page after having access it through query X, among other relevance indicators.
The same year Korolyov was launch also saw the launch of your b2b social mia strategy Yandex’s AI assistant, Alice, which has boost the use of voice search on the search engine.
Androma
Androma is coming in 2018. This latest update brings new improvements. As well as continuing to develop and enrich the learning of its intelligent algorithm so that searching for information becomes easier and more intuitive for users and the content offer is more relevant, more reliable. And comes from higher quality sources.
New features are coming , such as quick answers , which offer direct and clear results to simple queries. For example:
What day a particular holiday falls on.
Coffee shops near me.
Another new feature is Yandex.Experts , where users can ask anhui mobile phone number list questions on a wide variety of topics to real experts if they cannot find an answer to their query in the search results.
Conclusions
What conclusions can we draw from the direction Yandex has taken in recent years and how it affects SEO? In short, we do not see any major differences between Google and Yandex in this regard.
What football match is being play today?
Generating relevant, quality content continues to be a fundamental pillar. When creating content for our website, we must orient it towards the user, not the search engine. Correct and coherent writing that provides valuable information is the key.
Voice searches will become increasingly important.
What new developments in the Yandex algorithm do you think await us this year?
