Rank Brain

RankBrain
BY: MAGS
le R a n k B r a i n ?
W ha t is G oog
RankBrain is a component of Google's core algorithm which uses
machine learning (the ability of machines to teach themselves from data
inputs) to determine the most relevant results to search engine queries.
So: what makes RankBrain different?
Before RankBrain, 100% of Google’s algorithm was
hand-coded.
So the process went something like this:
Here's the craziest part:
Google asked a group of Google Engineers to identify the best page
for a given search. They also asked RankBrain, and RankBrain
outperformed brainy Google engineers by 10%!
Human engineers still work on the algorithm, of course. But today,
RankBrain also does its thing in the background.
In short, RankBrain tweaks the algorithm on its own.

Depending on the keyword, RankBrain will increase or decrease, the
importance of backlinks, content freshness, content length, domain
authority etc.
Then, it looks at how Google searchers interact with the new search
Lorem ipsum dolor sit
amet, consectetur
results. If users like the new algorithm better, it stays. If not, RankBrain
adipiscing elit. Donec
quis erat et quam.
rolls back the old algorithm.

RankBrain has two main jobs:
1. Understanding search queries (keywords)

2. Measuring how people interact with the results (user
satisfaction)
Let’s break each of these down.

How RankBrain Understands Any Keyword That You
Search For
Project 03
A few years ago, Google had a problem:
15% of the keywords that people typed into Google were never seen before.
15% may not seem like a lot. But when you process billions of searches per day, that
amounted to 450 million keywords that stumped Google every day.
Before RankBrain, Google would scan pages to see if they contained the exact
keyword someone searched for.
But because these keywords were brand new, Google had no clue what the searcher
actually wanted. So they guessed.
For example, let’s say you searched for “the grey console developed by Sony”.
Google would look for pages that contained the terms “grey”, “console”,
“developed” and “Sony”.
Not bad.
What changed? Before, Google would try to match the
words in your search query to words on a page.
Today, RankBrain tries to actually figure out what you

mean. You know, like a human would.
How? By matching never-before-seen keywords to

keywords that Google HAS seen before.
For example, Google RankBrain may have noticed that lots of people
search for “grey console developed by Nintendo”.
And they’ve learned that people who search for “grey console developed
by Nintendo” want to see a set of results about gaming consoles.
So when someone searches for “the grey console developed by Sony”,
RankBrain brings up similar results to the keyword it already knows
(“grey console developed by Nintendo”).
So it shows results about consoles. In this case, the PlayStation.
Another example: a while back Google published a
blog post about how they’re using machine learning
to better understand searcher intent:
Job description
In that post they describe a technology called “Word2vec” that turns
keywords into concepts.
For example, Google says that this technology “understands that Paris
and France are related the same way Berlin and Germany are (capital and
country), and not the same way Madrid and Italy are”.
Even though this post wasn’t talking specifically about RankBrain,
RankBrain likely uses similar technology.
In short: Google RankBrain goes beyond simple keyword-matching. It turns

your search term into concepts… and tries to find pages that cover that
concept.
Let’s cover the most interesting element of what RankBrain does…

How RankBrain Measures User Satisfaction
Sure, RankBrain can take a stab at understanding new keywords. And it
can even tweak the algorithm on its own.
But the big question is:
Once RankBrain shows a set of results, how does it know if they’re

actually good?
Well, it observes:
In other words, RankBrain shows you a set of search results that they think
you’ll like. If lots of people like one particular page in the results, they’ll
give that page a rankings boost.
And if you hated it? They’ll drop that page and replace it with a different
page. And the next time someone searches for that keyword (or a similar
term), they’ll see how it performs.
What is RankBrain observing exactly?
It’s paying very close attention to how you interact with the search results.
Specifically, it’s looking at:
1. Organic Click-Through-Rate
2. Dwell Time
3. Bounce Rate
4. Pogo-sticking
These are known as user experience signals (UX signals).
Organic click-through-rate (also known as “Organic CTR”),
is the percentage of searchers that click on a search engine
result. Organic CTR is largely based on ranking position but
is also influenced by a result’s title tag, description, URL and
presence of Rich Snippets.
Dwell Time is the amount of time that a Google searcher
spends on a page from the search results before returning
back to the SERPs. Many SEO professionals consider
Dwell Time an important Google ranking signal.
Bounce Rate is defined as the percentage of visitors
that leave a webpage without taking an action, such
as clicking on a link, filling out a form, or making a
purchase.
Pogo sticking is when a search
engine users visits several different
search results in order to find a
result that satisfies their search
query.
Let’s look at an example:
You pulled a muscle in your back playing tennis. So you search for “pulled
back muscle” in Google.
Like most people, you click on the first result. Unfortunately, the intro is
full of fluff and filler content (“Your back is an important muscle
group…”).
So you hit your back button and check out the 2nd result:
Bingo! This result is EXACTLY what you’re looking for.
So instead of hitting “back”, you spend 5 minutes reading through the page’s physical therapy routine. And because
you got what you wanted, you didn’t revisit the search results.
This back-and-forth is called “Pogo-sticking”. And it’s something that RankBrain pays a lot of attention to.
Well, if lots of people also Pogostick after clicking on the first result, that tells Google:
“The #1 result isn’t making our users happy. Let’s drop it down a few spots.”
If Google notices that people quickly leave a page to click on a different search result, that sends a strong message to
Google: “That page stinks!”.

How to Reduce Bounce Rate and Boost Dwell Time
Push Your Content Above the Fold
When someone clicks on your site from Google, they want
their question answered NOW.
In other words, they don’t want to scroll down to read your

content.
That’s why it is highly recommended removing anything

that pushes your content below the fold, like this:
Believe it or not, but I spend MORE time on my intros than my headlines.
That’s because your intro is where 90% of your readers decide to stay… or go.
And after A LOT of testing I’ve found that short intros work best.
Why?
When someone searches for something in Google, they already know about that
topic. So there’s no need for a massive intro.
2. Publish Long, In-Depth Content
I’ve tested this ten ways to Tuesday. And I can tell you with confidence that:
Longer content=better Dwell Time.
Obviously, it takes longer to read a 2000-word guide than a 400-word blog post. But that’s
only part of the equation.
The other reason that long form content improves Dwell Time is the fact that longer content
can fully answer a searcher’s query.
For example, let’s say that you search for “how to run a marathon”.
3. Break Up Your Content Into Bite Size Chunks
Let’s face it:
Reading 2,000 words is HARD.
And it’s even harder if those 2,000 words are presented as a giant wall of text.
Fortunately, there’s a simple way to get around this problem: subheaders.
Subheaders break up your content into digestible, bite-size chunks. This improves
readability, and therefore, Dwell Time.
THANK YOU!


Rank Brain

Uploaded by

Copyright:

Available Formats

Rank Brain

Uploaded by

Document Information

Original Description:

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Rank Brain

Uploaded by

Copyright:

Available Formats

RankBrain

In short, RankBrain tweaks the algorithm on its own.

rolls back the old algorithm.

1. Understanding search queries (keywords)

Let’s break each of these down.

Today, RankBrain tries to actually figure out what you

How? By matching never-before-seen keywords to

In short: Google RankBrain goes beyond simple keyword-matching. It turns

Let’s cover the most interesting element of what RankBrain does…

But the big question is:

Once RankBrain shows a set of results, how does it know if they’re

Google: “That page stinks!”.

In other words, they don’t want to scroll down to read your

That’s why it is highly recommended removing anything

Longer content=better Dwell Time.

Reading 2,000 words is HARD.

Fortunately, there’s a simple way to get around this problem: subheaders.

You might also like