Derral Eves - The YouTube Formula

Figure 4.1 Thumbnail with data points

Once the thumbnail has been checked, the AI goes through every single frame of the video and creates shot lists and labels based on what it sees in the content of the video itself. For example, if you do a video in a parking lot, the AI detects the store front, people, flowers, brands, and more, so it can log that info for recommendations and run it through the same safety routine that it uses to check thumbnail images. Be aware of what is in the frame in every scene of every video you create! It will be detected by the AI and sorted accordingly, because the AI is validating the thumbnail. The AI cuts through the “noise” of every single thing in every frame and determines what is most important according to that video and its metadata.

The AI does the same thing with the language of the video. YouTube has an auto‐caption feature now, and the AI reads through the words of the caption to gather data as well. So basically going through the video frames using shot lists is like looking at what is visually being said, while listening to the audio provides even more feedback via what is actually being verbalized. Everything goes into the system.

The AI is also listening for actual sentence structure and breaking it down into a sentence diagram. This extracts the meaning of what is being said. It can differentiate language so it can group it categorically, but not just on the surface. For example, two different creators might both talk about Stephen Hawking in their videos, but one video might be biographical or scientific while the other might be humorous or entertaining. Even though both videos are talking about the same person, they are categorically different enough that the AI would categorize them differently and group them with different recommended content because of the language being used.

As you should expect, the algorithm also looks at the video's title and description to supplement what it has already learned from the thumbnail, frame by frame, and the language. But it only tracks this as long as it needs to before it will use viewer data that comes in. The AI “knows” that people can be deceptive with metadata, but they can't lie about what's actually in the content. Don't slap a title and description on your video haphazardly just to get it finished and uploaded. The verbiage matters, so choose your words wisely. Most creators don't leverage the video description to its fullest potential. It's another data point the AI looks at to help with search ranking and discovery.

Did you know that YouTube has more than one algorithm? The AI uses multiple systems, and each has its own objective and goal. The surface features viewers see are:

Browse Features: Homepage and Subscription

Suggested

Trending

Notification

Search

Each of these features runs separate algorithms trying to be optimized for a higher hit rate, and they all feed into the YouTube AI. They have separate hit rates to determine what actually works for users in each particular system. Hit rate means how often viewers are able to find what they actually want to watch. Have you ever heard of a fisherman getting a “hit?” It's when a fish takes the bait. Imagine that you are the fisherman who has tossed his video into the water. Potential viewers are the fish swimming by your “bait.” Maybe 10 fish take a look at the bait and swim on by because it's not the brand of bait that they like. But along comes a fish who says, “That looks good,” and he bites. Say you toss this line 10 times, and while 100 fish swam past, 10 took the bait. There's your hit rate. This hit rate is so important to each system in the AI. The algorithms are very sensitive to user behavior and the metadata on each traffic source so that they know how to change to increase the hit rate.

Additionally, YouTube is constantly running experiments—several thousand a year—and they implement about 1 in 10 changes as they go, so this translates to hundreds of changes being implemented annually. These changes help the system get smarter, and smarter means better at feeding viewers what they will watch.

YouTube's Homepage has changed over time. Users no longer have to type a query in Search or to put in the work to navigate. The Homepage used to be where users saw only video recommendations of channels they had subscribed to. Now the Homepage has a personalized recommendation feed based on that user's history over time.

As long as a user is logged in when using YouTube, the algorithms can keep track of what videos that particular user has watched in the past so it can make better suggestions for videos that user is likely to watch, even if they haven't watched those videos in the past. This seems counterintuitive. It seems like the algorithm could be more successful suggesting videos it knows a user has already watched and liked, but actually the opposite is true. Keeping suggestions fresh actually gets users to stick around on the platform longer because they aren't getting bored with the same old stuff.

How YouTube does this is by breaking down the Homepage into two categories: familiar and discovered. It shows users familiar content from places the viewer has gone to before. These suggestions could include trending or recent videos from a channel a viewer has already watched. The discovery side includes videos or channels that users with similar viewing patterns have watched and liked. YouTube has found that these combined strategies are keeping viewers better engaged. If you want to get on the Homepage—and this definitely should be your goal—learn the triggers that get videos there. Try to improve your click‐through rate and audience retention, because these will help you get pushed out to a more general audience.

This one doesn't need a lot of explanation. The Subscription section pulls content from channels you've already subscribed to. It will suggest new videos from your subscribed channels, especially new videos with similar content to what you've consumed before. For example, you watched a prank video or two from a channel you have subscribed to, so the AI pulls that channel's newest prank into your Subscription feed.

Another place besides the Homepage creators should be focusing on is Suggested feed, including the “Up Next” video. These are the suggestions below (on mobile) or to the right (on desktop) of the video that is being watched. This is a powerful place to be! Viewers stick around when this feature is working really well, and sticky viewers are YouTube's goal. So if you can use the triggers to get your video in the Suggested feed, you're exactly where you need to be.

What are the triggers? First, make sure you have created a strong relationship among the data in your own content. This means that if the metadata connects among your videos, the algorithm plugs your videos into the Up Next feed, and your video's likelihood of being watched skyrockets. Metadata includes title, keywords, description, and the content itself. We talk in depth about metadata in Part IIIof the book. The viewers' behaviors trigger which videos get put in the Suggested feed as well, so when your content keeps viewers watching instead of bouncing, your content is more likely to be recommended here.