Google Launches Neural Matching Algorithm

First up was Google's new E-A-T evaluation criteria and more recently Google has announced they are starting to use a “neural matching” algorithm to better understand certain concepts. 

According to Google’s Danny Sullivan, the new algorithm is being tested on 30% of search queries. When you consider the sheer number of Google searches per day that's a large number of searches now being run on this new code base.

What does the algorithm actually do?

The purpose of the algorithm is to match a search query to a web page, using only the search query and the web page itself. Web pages ranked by this kind of algorithm will not have been promoted to the top positions by links or keywords since this kind of algorithm is about “relevance matching.”

Effectively eliminating many of Google's SEO best practice guidelines from affecting rankings. Which is a scary thought considering the amount of time and effort some sites put into making sure their web pages are optimised for better organic performance. 

Matching searches based only on relevance may seem like a great idea, but it also leaves room for poor quality content to rise to the top. Since users will see content based on their intent and not intent + authority.

Content is more important

So why the need for neutral matching you ask? Simple, Google wants content to be the key driver of search relevance while other factors become less and less important over time. 

Larger sites have been getting away with attracting traffic simply because their other ranking signals are high but produce poor content and have been riding the wave for too long. 

A practice SEO's know all too well, and a trend Google aims to put a stop to.

What should we take from this update?

This machine learning update isn't simply about matching keywords to content, but keyword intent expressed and matched it to content that matches the context of that expression. 

What Google has officially stated is that it can understand concepts. So in a way, that goes beyond mere keywords and synonyms. It’s a more natural understanding of how a web page solves the problem implied in a search query. According to Google’s official announcement:

“…we’ve now reached the point where neural networks can help us take a major leap forward from understanding words to understanding concepts. Neural embeddings, an approach developed in the field of neural networks, allow us to transform words to fuzzier representations of the underlying concepts, and then match the concepts in the query with the concepts in the document. We call this technique neural matching.”

Is neural matching here to stay?

This new kind of AI ranking shows how it’s possible to generate search results that are not directly ranked by traditional ranking factors like links or keywords. 

This update will demand closer attention to things like user intent and understanding how a page of content helps a user. It will also encourage content creators to produce richer content pieces in a variety of methods to match the different user intents expressed in a search. 

Overall, Google is trying to encourage users to create multiple resources and make sure their content is of the highest quality and the most helpful if they are to gather organic search traction over time.

Should you be worried about neural matching?

At this moment in time, I would have to say no! Google would not risk disrupting the currently profitable search algorithm in favour of neural matching across the board. 

What I think Google is doing is trying to capture enough data as possible using this algorithm and then looking at ways to apply it in conjunction with the current system or have it take the lead on certain types of queries were it produces the best relevancy results. In short, SEO is not dead, so stick to your best practices and keep optimising!

Contact us

If you want to know more about search engine marketing for your site, don’t be shy we’re happy to assist. Simply contact us