Source: How-To Geek
With over a billion users and billions of hours of video, the fact that YouTube’s algorithm manages to deliver what you want to watch when you visit the site is a testament to software engineering. So, how does it work?
The short answer: Nobody knows the details—not even YouTube, to an extent.
YouTube’s algorithm uses machine learning to suggest videos, which means there are no set rules we can tell you. Besides, Google wouldn’t tell us anyway, as that would lead to people exploiting them.What We Do Know
When you train a machine learning model, you give it a bunch of input and then rank its suggested outputs on how right they are.
Here’s a greatly oversimplified example. Say you wanted to train an AI to tell the difference between pictures of cats and dogs. Essentially, you’d give an AI a bunch of pictures of cats and dogs, have it start choosing, and then score it right if it answered correctly. The more it gets correct, the better it gets at choosing. The result is a machine that can identify cats and dogs. This training uses a metric by which results are judged; in our case, the cat-o-meter, or what percent of the image is indeed cat.
The metric YouTube uses is watch time—how long users stay on the video. This makes sense because YouTube doesn’t want people skipping around looking for videos to watch, as that’s more work on their end, and less time spent watching.
It’s much more nuanced than just “how long you watched a video,” though. The algorithm takes into account many different factors and ranks them accordingly: viewer retention, impressions to clicks, viewer engagement, and some other behind the scenes factors that we never see. YouTube then tailors these factors to your profile so that it can suggest videos you’re more likely to click.
What to Take Away From This
If you’re an aspiring YouTuber, the two main things to work on are maximizing your average view duration, and maximizing your click-through rate. Take the following upside-down pyramid.
The post How Does the YouTube Algorithm Work? appeared first on FeedBox.