YouTube usually isn’t known for being super transparent with creators or advertisers about how the proverbial sausage is made. So in this article we’re going to take a look at the history of YouTube’s priorities when it comes to helping viewers discover new videos. We’re going to lay out how the algorithm works, as well as all the latest YouTube algorithm changes for 2020.
Bonus:Download a free guide that reveals the exact steps one creator took to gain more than 23,000,000 views on YouTube with no budget and no expensive gear.
A brief history of the YouTube algorithm
YouTube’s first video was uploaded in 2005. Fifteen years later, people are uploading 500 hours of video to the platform every minute.
How do 2 billion users find what they want to watch? The short answer is that it’s changed over the years. But here’s the long answer, too:
2005-2012: View count (a.k.a. clicks)
For the first seven years, YouTube rewarded videos that got clicks, rather than the ones that kept users engaged.
Obviously, this system had a tendency to show people a lot of clickbait: misleading titles and thumbnails proliferated. Users would click, but then feel tricked, probably a little annoyed, and then abandon videos partway through. Eventually, YouTube realized that their user experience was going down the drain and changed tacks.
2012: Watch time (a.k.a. view duration)
In 2012, the platform announced an update to the discovery system designed to identify the videos people actually want to watch. By prioritizing videos that hold attention throughout (as well as increasing the amount of time a user spends on the platform overall) YouTube could assure advertisers that it was providing a valuable, high-quality experience for people.
Meanwhile, YouTube was also encouraging creators to stop fussing with algorithm optimization (i.e., making videos shorter to get a higher retention rate, or making them longer in order to rack up more watch time).
Instead, as it still does today, YouTube encouraged people to just “make videos people want to watch.”
2016: Machine learning (a.k.a. the algorithm)
In 2016, YouTube released a whitepaper that made some waves. In it, product engineers described the role of deep neural networks and machine learning in the platform’s recommendation system.
Of course, for all the impressive jargon, this whitepaper wasn’t a tell-all. You can read it, but even if you understand it (or get your smart friend to explain it to you), it’s not the equivalent of Coca-Cola’s secret recipe. (It’s more like if Coca-Cola announced that the reason their beverage is so tasty is because it undergoes a carbonation process and also there is sugar in it.)
At this point, we still don’t know that many details about what’s under the YouTube algorithm’s hood. But we do know that it tracks viewers’ perceived satisfaction to create an addictive, personalized stream of recommendations.
2016-2020: Borderline content, demonetization and brand safety
For the past few years, YouTube has faced plenty of questions about the type of videos its algorithm surfaces and promotes (or doesn’t).
According to YouTube CEO Susan Wojcicki, YouTube is taking its responsibilities seriously, and trying to balance a broad, fair range of opinions with making sure that outright dangerous information doesn’t spread. For instance, YouTube says that algorithm changes in early 2019 have led to 70% less watchtime for “borderline” content. (Borderline content is defined as content that doesn’t quite violate the platform’s community guidelines, but is harmful or misleading.)
It’s a complicated issue because it touches every issue: from white supremacy to the coronavirus. For instance, in March 2020, YouTube creators say the platform was demonetizing videos that so much as alluded to the existence of the coronavirus. YouTube’s position, meanwhile, is that it wants to support a diversity of opinions (i.e., how governments should respond to the coronavirus) but not the dangerous ones (i.e., videos saying the virus is a hoax, or that drinking hand sanitizer will cure it). Wojcicki announced that “when people come to YouTube searching for coronavirus topics, on average 94% of the videos they see in the top 10 results come from high-authority channels.”
Regardless of where you stand, the developments are ongoing, so this is an important discussion for both creators and advertisers to keep informed about.
If you’re a creator, remember that just because the algorithm is rewarding the content you make with high visibility and ad revenue doesn’t mean YouTube won’t turn around and demonetize your channel or video if your content crosses the line into something advertisers find objectionable.
Meanwhile, advertisers need to know that their sneaker ads aren’t funding anti-vaxxers or conspiracy theorists. The YouTube algorithm in its current form is designed to demonetize borderline content, mostly to protect brands. At the same time, YouTube says says it might never be able to guarantee 100% brand safety.
How does the YouTube algorithm work in 2020?
According to YouTube, the algorithm is basically a “real-time feedback loop that tailors videos to each viewer’s different interests.” It decides which videos will get suggested to individual users.
The algorithm’s goals are twofold: find the right video for each viewer, and get viewers to keep watching. Therefore, the algorithm is watching user behavior as closely as it watches video performance.
The two most important places the algorithm impacts are search results and recommendation streams.
How the YouTube algorithm influences search results
Unsurprisingly, the videos you get when you search “carnivorous house plants” will be different from the videos I get when I search “carnivorous house plants.” Search results are based on factors like:
Your video’s metadata (title, description, keywords) and how well those match the user’s query
Your video’s engagement (likes, comments, watch time)
How the YouTube algorithm influences recommended videos
The recommendation stream is a two-fold process for the algorithm.
First, it ranks videos by assigning them a score based on performance analytics data. (Scroll down for our list of all known factors.)
Second, it matches videos to people based on their watch history, and what similar people have watched.
The idea is not to identify “good” videos, but to match viewers with videos that they want to watch. The end goal is that they spend as much time as possible on the platform (and therefore see as many ads as possible.)
For the record, there are three other places the algorithm makes a big impact:
Your YouTube homepage
How YouTube determines the algorithm
While we don’t work at Google, here’s a running list of all the different factors that YouTube has mentioned in its various public discussions of the algorithm over the years.
When it ranks a video, the algorithm looks at performance:
Whether people click on a video (a.k.a. impressions vs. views: thumbnail, and title are important, here)
How much time people spend watching a video (watch time, or retention)
How many likes, dislikes, comments or shares a video gets (a.k.a. engagement)
How quickly a video’s popularity snowballs, or doesn’t (this is called view velocity, rate of growth)
How new a video is (new videos may get extra attention in order to give them a chance to snowball)
How often a channel uploads new videos
How much time people spend on the platform after watching a video (session time)
When it matches a video to a potential viewer, the algorithm looks at personalization:
Which channels and topics have they watched in the past?
What have they engaged with in the past?
How much time do they spend watching?
How many times has this video already been surfaced for this person?
What don’t they watch?
7 tips to improve your organic reach on YouTube
Here’s our list of tied and true methods for playing nice with the algorithm.
1. Optimize your video description text
Contrary to popular belief, that block of text underneath your video isn’t just a place to link to your socials (although you should definitely do that, too.) It also helps the algorithm surface your video when users are searching for your topic. So make sure you front-load the first sentence with a clear, keyword-focused description of your video.
As in the above examples, make you sure you:
Use natural language, not keyword salad
Focus on one or two keywords and repeat them in both your description and title
For instance, this local dad started a channel during the pandemic lockdown, and his premise—answering questions people might usually ask their dad, if, like him, they don’t have one—has racked up 2.4 million subscribers in two months. It’s a unique, earnest and emotional value offering, and it’s extra-impressive because this channel succeeded in a content vertical (that is, DIY how-to videos) that seemed pretty much saturated.
Quantity of videos, and frequency of upload, is an important factor for the algorithm, and YouTube’s home screen especially. (It’s that personalized list of new and interesting videos that’s kind of like Instagram’s Explore page).
If you can increase quantity without losing quality, go for it. The more videos you publish, the better chance you’ll have of hitting the right nerve. Maybe you can turn that one big hit into a series. Or you could introduce a new, low-effort weekly feature that fits into your brand’s established niche; like a Tuesday reaction video or a Wednesday study with me session or a Thursday Twitch stream.
4. Make your videos public when your audience is watching
5. Keep viewers engaged throughout the whole video
Another key performance metric for the algorithm is view duration. You might see advice that advocates for making your videos shorter or longer, but really, just make them as interesting and fun to watch as you possibly can.
For instance, this six-minute video of a bratty raven chatting at her best friend is solid across the board. Our educated guess is that not just clickability but retention (a.k.a. view duration) helped this video’s views skyrocket. (This was the channel’s breakout video, hitting 4 million views when their average is usually well under a million.)
Once you’ve charmed people to watch through to the end, you can then go ahead and use end cards and/or playlists (See #6 in our list of ways to get more YouTube views) to suggest that they watch your next video. Because no one needs a recommendation algorithm if people trust your recommendations, right? Right.
6. Engage with your community
We’ll never stop saying this. Reply to your comments. Talk to your people. Just remember that the algorithm “knows” if you’re having meaningful conversations or just paying lip service to bump up your vanity metrics.
If you’re in the position of having too many people to respond to, you can always do an appreciation video. Like this video, where this illiterate fox gets to hear all the compliments people type to him.
If no one sends you tens of thousands of compliments every week about the cute noises you make, that’s ok too. You can skip the video and manage conversations for your channel using Hootsuite. Like so:
7. Turn viewers into subscribers
According to YouTube, your channel’s subscribers provide a bunch of important initial signals that help dictate the success of your video. In other words, these fans are the testing ground—if they love it, the algorithm is more likely to show the video to new eyeballs.