Technology & Computing · Digital life & society

How recommendation feeds decide what you see

Follow how a feed narrows billions of items to a screenful, what its score rewards, and how the design of a screen steers the choices you make.

4 short lessons · about 17 minutes · 4 sources · updated November 2026

What you will learn

  • Distinguish selecting candidates from ranking them.
  • Explain why a recommendation isn't an independent judgment of importance.
  • Explain how optimizing clicks can favor a misleading headline.
  • Distinguish a measurable proxy from the user benefit it's meant to represent.

Lesson 1 of 4 · 4 min

How a feed picks a few videos out of billions

Before you readWhat share of YouTube watch time does Google say comes from recommendations?

Correct.Not quite. The answer is 60%.

Google says 60% of watch time comes from recommendations. This lesson shows how a feed picks a few videos out of billions.

YouTube holds billions of videos, and your home screen shows a handful. Something had to choose. Google says 60% of watch time on YouTube comes from recommendations, so most viewing starts with that choice.

A search begins with words you typed. A recommendation system offers things you didn't know to ask for. So the way it narrows billions down to a screenful shapes what you end up watching.

No system can study billions of videos in detail every time you open the app. So a common design works in two stages.

Candidate generation comes first. It cheaply pulls a much smaller pool from several sources, such as videos related to ones you've watched, what's popular or trending, and what your friends liked. Ranking comes second. A more careful model scores each candidate in the pool and sorts them.

Say the pool comes down to a cooking demonstration, a comedy clip and a repair tutorial. The ranking model gives each one a score. A typical score is a prediction, such as the probability that you'll watch this video, worked out from your watch history, your language and country, the time and the video's own details.

The highest score goes first. What you can't see from outside is which prediction the system was built to make. Two services could rank the same three videos differently and both be working as designed.

Check yourselfIn a recommendation system, what's the main difference between candidate generation and ranking?

Correct.Not quite. The answer is Candidate generation gathers possible options, and ranking puts them in order.

Candidate generation narrows a huge collection to a small pool, cheaply. Ranking then scores that pool in detail and sets the order. Narrowing first is what makes the careful scoring affordable.

The sorted list still isn't final. A re-ranking stage applies extra rules. It can remove candidates, such as videos a separate model has flagged as clickbait. It can adjust scores to favor newer videos. And it can add variety, because the closest matches tend to be near-copies of each other. Google's course imagines a viewer shown nothing but owl videos, who soon loses interest.

So the order on your screen doesn't follow one score from top to bottom. People chose the rules, the goal and the signals, even where a model does the arithmetic.

Try to recallWhy doesn't appearing first in a recommendation list prove an item is the most important?

The top spot goes to whatever scores highest on the system's chosen prediction, such as how likely you are to watch, after re-ranking rules for things like freshness and variety. None of that measures importance or truth.

Lessons in this topic

  1. How a feed picks a few videos out of billions

    Follow a recommendation from the candidates a system gathers, through scoring and re-ranking, to the short list on your screen.

    Essentials · 4 min

  2. Why a feed that chases clicks learns clickbait

    See what happens when a recommender is told to maximize clicks or watch time, and why neither number equals a satisfied viewer.

    Essentials · 4 min

  3. Dark patterns and the choices a screen steers you into

    Learn to spot designs that hide or obstruct a choice, and see why the position of an item on a screen distorts what a feed learns about you.

    Deeper · 4 min

  4. Two ways a recommender guesses what you'll like

    Compare recommendations based on similar items with ones based on similar people, and see why a brand-new video is hard for a feed to place.

    Deeper · 5 min

Three quick stories from this topic

The mischievous genie

A feed told only to maximize clicks can end up promoting clickbait

Google's course for engineers compares machine learning to a mischievous genie that grants exactly the wish you state. Reward clicks and it may serve clickbait. Reward watch time and it may favor very long videos. Neither number means the viewer was glad they watched.

The measure is a substitute

Clicks are easy to observe. Satisfaction and learning are harder to measure. A proxy helps you count something, but it never becomes the human benefit it stands for.

Ask what the user wanted

A short answer that lets someone finish a task may beat a long session. Staying engaged and getting something done are different outcomes.

Most YouTube viewing is recommended

Google says recommendations account for 60% of the time people spend watching YouTube

The figure comes from Google's own course for engineers, which adds that 40% of app installs on Google Play come from recommendations too. So more than half of all YouTube viewing starts with a choice a ranking system made.

Billions in, a screenful out

YouTube holds billions of videos. A recommender first gathers a small pool of candidates, then scores and sorts them, then adjusts the list for things like freshness and variety.

Where an item sits matters too

Items higher on a screen get clicked more than items lower down. Engineers call it positional bias, and it means a click count partly measures placement.

Fake countdown timers

The FTC counts fake countdown timers among the design tricks it calls dark patterns

The timer suggests an offer is about to end when it isn't. The agency's 2022 report also lists ads disguised as independent articles, fees revealed only late in a purchase and subscriptions made hard to cancel.

A case the FTC brought

The FTC alleged that the online learning site ABCmouse promised 'Easy Cancellation' while making it extremely difficult to cancel free trials and subscriptions.

Why it works

Extra effort on one path changes what people do. So a count of customers who stayed subscribed reflects the design of the screen as well as what they wanted.

Sources

This topic is part of What happens behind the screen, a guided path through related topics.

  • How cookies let websites remember and track you

    A cookie is a small note a server asks your browser to keep and hand back. See why the web needs them, how one company can use them to follow you across sites, and what browsers do about it.

    4 lessons · 25 min

  • Social media

    See how social networks grew from friend lists into feeds of strangers' videos, why they cost nothing to use, why the leading app differs by country, and what experiments say about their effect on politics.

    4 lessons · 16 min

  • Online advertising and free services

    Search, maps and social apps cost nothing because advertisers pay for your attention. See how one ad slot is auctioned while a page loads, how ads get targeted and measured, and where fraud and blockers bite.

    4 lessons · 16 min

  • How the internet works

    The internet is tens of thousands of separate networks that agree to carry each other's traffic. See how data is cut into packets, how routers pass them along, and how they're put back together.

    4 lessons · 16 min

  • How a database keeps records consistent

    See how transactions, built-in rules and isolation levels keep records right when a server crashes, two buyers want one seat or two updates collide.

    4 lessons · 17 min

  • How processors execute instructions

    Follow a tiny calculation through the instructions, memory addresses and circuits that make a computer work.

    4 lessons · 22 min

All technology & computing topics · Take the quiz