Here is a question: how does a video site know what to show you next? The answer is a recommendation system, and it is worth taking apart piece by piece. A research article defines recommender systems as software tools and techniques providing users with suggestions for items a user may wish to utilise. Recommendation systems learn from what people do, such as what they watch and click on. To a first approximation, generating a user's feed is a matter of ranking all the posts that can be shown. For every post in a user's feed, the algorithm receives feedback about whether and how the user engaged with it. As of August 2026, Common Sense Media says YouTube's algorithm plays a big role in what kids and teens see.

Next, look at how the choosing is split into steps, one step after another. The scale of the system is part of the story. A 2016 Google research paper says YouTube represents one of the largest scale and most sophisticated industrial recommendation systems in existence. In one common recommendation design, the system starts from a potentially huge collection and generates a much smaller subset of candidates. Candidate generation is the first stage of recommendation: given a query, the system generates a set of relevant candidates. A given recommendation model may provide multiple candidate generators, each nominating a different subset of candidates. The model that generates candidates needs to evaluate queries quickly given the enormous size of the corpus. Then the engagement prediction and ranking algorithm is applied only to a smaller set of candidate posts.

Here is a different question: what does a system compare when it picks? After candidates come scoring and re-ranking. In a scoring stage, the system can use a more precise model relying on additional queries. In a re-ranking stage, the system can remove items the user explicitly disliked or boost the score of fresher content. The systems also differ in what they compare. Google's course notes give an example: if user A watches two cute cat videos, the system can recommend cute animal videos to that user. In collaborative filtering, if user A is similar to user B and user B likes video 1, the system can recommend video 1 to user A. In a recommendation system, two users are similar if they have engaged with a similar set of posts.

Next, here is what YouTube said about its own system, with the dates it gave. In a September 2021 post, YouTube said its system sorts through billions of videos to recommend content tailored to a viewer's specific interests. In 2021 YouTube said its system learns every day from over 80 billion pieces of information it calls signals. YouTube said its system does not follow a set formula but develops dynamically as a viewer's habits change. YouTube also said people are, on average, more likely to be satisfied by videos that they share or like. It said its system uses this information to predict the likelihood that a viewer will share or like further videos. These statements are dated September 2021.

Here is the next piece: clicks and watching are not the same thing. In its September 2021 post, YouTube said clicking on a video is a strong sign that a viewer will also find it satisfying. In the same post, YouTube said it learned in 2011 that clicking on a video does not mean the viewer actually watched it. Before 2012, YouTube optimized for click-through rate instead of watch time, which the Knight Institute says led to clickbait thumbnails. YouTube said that when it first added watch time to recommendations it saw an immediate 20% drop in views. YouTube said it asks why a viewer gave a video a one- or two-star rating, and that only videos rated four or five stars are counted as valued watch time.

Next, look at what the system tries to predict. As of November 2026, the Knight Institute explainer says YouTube optimizes for expected watch time: how long the algorithm predicts the video will be watched. As of November 2026, the explainer also says that if a user sees a video in their recommendations and does not click on it, the watch time counts as zero. As of November 2026, it says Netflix originally optimized for suggesting movies that the user is likely to rate highly on a scale of one to five. As of November 2026, Common Sense Media says YouTube's business model rewards watch time: the longer users watch, the more YouTube makes in ad sales. In a Columbia Knight Institute explainer, engagement means any score defined only in terms of the moment-to-moment actions of the user.

Here is more of what YouTube said, followed by what outside groups say. YouTube also described how it handles quality in September 2021. YouTube said a dislike is a signal that the viewer probably did not enjoy watching the video. It said its recommendation system is getting better every day thanks to feedback, but it can always be better. YouTube said surveys show borderline content is satisfying to only a very small portion of viewers. As of August 2026, Common Sense Media says the YouTube algorithm isn't designed with kids in mind and is designed to keep users engaged. It also says YouTube's Up Next feature and autoplay encourage hours of uninterrupted viewing, often leading kids to lose track of time. As of November 2026, KidsHealth says most apps, games and streaming platforms are designed to keep users involved as long as possible.

Here is the next question: who may use these sites, and what do the rules say? Age rules come next, with the facts dated November 2026 unless noted. YouTube's terms of service say you must be at least 13 years old to use YouTube, though children of all ages may use YouTube and YouTube Kids if a parent or guardian enables it. For children under the minimum age, parents can help create and manage a Google Account with Family Link. In a 2019 news report, a YouTube spokesperson said YouTube is not a site for people under 13. YouTube says a teen must have a Google Account that meets the minimum age requirements in their country or region. YouTube says a parent can set up a supervised account and link it with a teen's account. When a supervised account is linked, a parent can get insight into a teen's YouTube activity.

Here is the next question: what rules cover a child's personal information online? These facts are dated November 2026. Under the COPPA Rule, photos, videos and audio recordings that contain a child's image or voice count as personal information. Websites covered by COPPA must notify parents and get their approval before collecting a child's personal information. COPPA applies only to websites and online services that collect, use or disclose personal information from children. Google's Family Link lets families customize parental controls on YouTube and set up parental controls for a YouTube Kids account. The COPPA Rule was designed to protect children under age 13.

Next, look at the version made for younger viewers. As of November 2026, these facts are about YouTube Kids. In YouTube Kids, pausing search or watch history means the videos watched or searched for are not used to recommend videos. In YouTube Kids, a parent can stop new video views from being used as signals to recommend other videos. YouTube Kids says it has limited advertising so that it can provide an experience at no charge. Controls made for kids are not perfect, and a child may still see something a parent did not want. If a child's profile is set to Approved content only, Recommended videos are drawn from content the parent has approved.

Next, here is what a viewer can do about the picks, and about the clock. A viewer has real controls over recommendations, as of November 2026. On certain pages, such as Home and Watch Next, a viewer can mark a video as Not interested. YouTube says that if a viewer deletes watch history, it won't base future video recommendations on that content. YouTube says it may also use data from a viewer's Google Account activity to influence recommendations and search results. YouTube says topics are based on a viewer's existing personalized suggestions and on content related to what they interact with. If Autoplay is on and a viewer wants to stop the next video, they can tap Cancel at the end of a video. On the Time management tab, a YouTube viewer can change the Take a break reminder and Auto-play settings. YouTube's help page gives one example of turning off watch or search history: researching a subject for a school project that you are not personally interested in.

Families have plans for screens too, as of November 2026. KidsHealth suggests preschoolers aim for no more than 1 hour a day of high-quality programming, and watch together when you can. KidsHealth says a reasonable starting point for kids and teens 5 to 18 is 1 to 2 hours of entertainment screen time a day, not including homework. The American Academy of Pediatrics' family media plan advises turning off devices that are not in use to reduce distractions. It advises keeping room for other activities so screens do not crowd out other important experiences. It says plans should evolve as a child matures and develops, and that every family is different, so a plan should fit its routines and values. The CDC says children and adolescents 6 to 17 need to be active for at least 60 minutes every day.

Words to know

• algorithm: step-by-step rule
• candidates: possible picks
• autoplay: automatic next video
• signals: pieces of information
• engagement: user actions