How Search algorithms work

With the amount of information available on the web, finding what you need would be nearly impossible without some help sorting through it. Google ranking systems are designed to do just that: sort through hundreds of billions of webpages in our Search index to find the most relevant, useful results in a fraction of a second, and present them in a way that helps you find what you’re looking for.

These ranking systems are made up of not one, but a whole series of algorithms. To give you the most useful information, Search algorithms look at many factors, including the words of your query, relevance and usability of pages, expertise of sources and your location and settings. The weight applied to each factor varies depending on the nature of your query – for example, the freshness of the content plays a bigger role in answering queries about current news topics than it does about dictionary definitions.

To help ensure that Search algorithms meet high standards of relevance and quality, we have a rigorous process that involves both live tests and thousands of trained external Search Quality Raters from around the world. These Quality Raters follow strict guidelines that define our goals for Search algorithms and are publicly available for anyone to see.

Learn more below about the key factors that help determine which results are returned for your query:

  • Meaning of your query

    Meaning of your query

    To return relevant results for your query, we first need to establish what information you’re looking for – the intent behind your query. Understanding intent is fundamentally about understanding language, and is a critical aspect of Search. We build language models to try to decipher what strings of words we should look up in the index.

    This involves steps as seemingly simple as interpreting spelling mistakes, and extends to trying to understand the type of query you’ve entered by applying some of the latest research on natural language understanding. For example, our synonym system helps Search know what you mean by establishing that multiple words mean the same thing. This capability allows Search to match the query 'How to change a light bulb' with pages describing how to replace a light bulb. This system took over five years to develop and significantly improves results in over 30% of searches across languages.

    Beyond synonyms, Search algorithms also try to understand what category of information you are looking for. Is it a very specific search or a broad query? Are there words such as 'review' or 'pictures' or 'opening hours' that indicate a specific information need behind the search? Is the query written in French, suggesting that you want answers in that language? Or are you searching for a nearby business and want local info?

    A particularly important dimension of this query categorisation is our analysis of whether your query is seeking out fresh content. If you search for trending keywords, our freshness algorithms will interpret that as a signal that up-to-date information might be more useful than older pages. This means that when you’re searching for the latest 'NFL scores', 'dancing with the stars' results or 'exxon earnings', you’ll see the latest information.

  • Relevance of webpages

    Relevance of webpages

    Next, algorithms analyse the content of webpages to assess whether the page contains information that might be relevant to what you are looking for.

    The most basic signal that information is relevant is when a webpage contains the same keywords as your search query. If those keywords appear on the page, or if they appear in the headings or body of the text, the information is more likely to be relevant. Beyond simple keyword matching, we use aggregated and anonymised interaction data to assess whether search results are relevant to queries. We transform that data into signals that help our machine-learned systems better estimate relevance.

    These relevance signals help Search algorithms assess whether a webpage contains an answer to your search query, rather than just repeating the same question. Just think: when you search for 'dogs', you probably don’t want a page with the word 'dogs' on it hundreds of times. With that in mind, algorithms assess if a page contains other relevant content beyond the keyword 'dogs' – such as pictures of dogs, videos or even a list of breeds.

    It’s important to note that, while our systems do look for these kind of quantifiable signals to assess relevance, they are not designed to analyse subjective concepts such as the viewpoint or political leaning of a page’s content.

  • Ranking useful pages

    Ranking useful pages

    For a typical query, there are thousands, even millions, of web pages with potentially relevant information. So to help rank the best pages first, we also write algorithms to evaluate how useful these web pages are.

    These algorithms analyse hundreds of different factors to try to surface the best information the web can offer, from the freshness of the content, to the number of times your search terms appear and whether the page has a good user experience. In order to assess trustworthiness and authority on its subject matter, we look for sites that many users seem to value for similar queries. If other prominent websites on the subject link to the page, that’s a good sign that the information is of high quality.

    There are many spammy sites on the web that try to game their way to the top of search results, through techniques like repeating keywords over and over or buying links that pass PageRank. These sites provide a very poor user experience and may even harm or mislead Google’s users. So we write algorithms to identify spam and remove sites that violate Google’s webmaster guidelines from our results.

  • Usability of webpages

    Usability of webpages

    When ranking results, Google Search also evaluates whether webpages are easy to use. When we identify persistent user pain points, we develop algorithms to promote more usable pages over less usable ones, all other things being equal.

    These algorithms analyse signals that indicate whether all our users are able to view the result, like whether the site appears correctly in different browsers; whether it is designed for all device types and sizes, including desktops, tablets and smartphones; and whether the page loading times work well for users with slow Internet connections.

    Since website owners can improve the usability of their site, we work hard to inform site owners in advance of significant, actionable changes to our Search algorithms. For example, in January 2018 we announced that our algorithms would begin to consider the 'page speed' of sites, six months before the changes went live. To aid website owners, we provided detailed guidance and tools like PageSpeed Insights and Webpagetest.org so site owners could see what (if anything) they needed to adjust to make their sites more mobile friendly.

    You can find more information on the tools and tips Google provides to site owners here .

  • Context and settings

    Context and settings

    Information such as your location, past Search history and Search settings all help us to tailor your results to what is most useful and relevant for you in that moment.

    We use your country and location to deliver content relevant for your area. For instance, if you’re in Bristol and you search 'football', Google will most likely show you results about English football and Bristol City first. Whereas if you search 'football' in London, Google will rank results about football and the Premier League higher. Search settings are also an important indicator of which results you’re likely to find useful, such as if you set a preferred language or opted in to SafeSearch (a tool that helps filter out explicit results).

    In some instances, we may also personalise your results using information about your recent Search activity. For instance, if you search for 'Barcelona' and recently searched for 'Barcelona vs Arsenal', that could be an important clue that you want information about the football club, not the city.

    Search also includes some features that personalise results based on the activity in your Google account. For example, if you search for 'events near me' Google may tailor some recommendations to event categories we think you may be interested in. These systems are designed to match your interests, but they are not designed to infer sensitive characteristics like your race, religion or political party.

    You can control what Search activity is used to improve your Search experience, including adjusting what data is saved to your Google account, at myaccount.google.com. To disable Search personalisation based on activity in your account, turn off Web & App Activity.