Skip to the lesson

Data and machine learningLesson 6 of 6

Part 1 of 3, 0 done

14 min

Because you watched…

In 2015, Netflix said its recommendations steered most of what members watched. Build the "people like you also liked" engine by hand, and find out why a feed can keep showing you more of the same.

Ticket 01 · The guess

How much does the recommender steer?

Netflix's home page is rows of picks chosen for each member. In 2015, two Netflix leaders described how its recommendation system works. What share of the hours members streamed did they say it influenced?

50%
0%100%
Words to know

Spot something wrong?

Tell us what looks off. No name or email needed.

What kind of problem?

0 / 1000

We'll also send this page, the lesson, ticket 1, so we can find it. Nothing else. Privacy

·
Sources and every number (1)

Sources

  • The Netflix Recommender System: Algorithms, Business Value, and Innovation (ACM Transactions on Management Information Systems 6(4), article 13) · ACM (Carlos A. Gomez-Uribe and Neil Hunt, Netflix), 2015

Every number

  • 80%doi.org ·2015 · Share of hours streamed on Netflix that its recommender influenced, about, as the company's leaders described it in 2015.
  • 20%doi.org ·2015 · Share of hours streamed that came from search, the remainder, as described in 2015.
  • 40 rowsdoi.org ·2015 · Rows of recommendations on a Netflix home page, roughly, as shown in the paper's figure (2015).
  1. Lessons›
  2. The school›
  3. Data and machine learning
  • ·Before this: Biased data, biased predictions
Skip to the lesson

Data and machine learningLesson 6 of 6

Part 1 of 3, 0 done

14 min

Because you watched…

In 2015, Netflix said its recommendations steered most of what members watched. Build the "people like you also liked" engine by hand, and find out why a feed can keep showing you more of the same.

Ticket 01 · The guess

How much does the recommender steer?

Netflix's home page is rows of picks chosen for each member. In 2015, two Netflix leaders described how its recommendation system works. What share of the hours members streamed did they say it influenced?

50%
0%100%
Words to know

Spot something wrong?

Tell us what looks off. No name or email needed.

What kind of problem?

0 / 1000

We'll also send this page, the lesson, ticket 1, so we can find it. Nothing else. Privacy

·
Sources and every number (1)

Sources

  • The Netflix Recommender System: Algorithms, Business Value, and Innovation (ACM Transactions on Management Information Systems 6(4), article 13) · ACM (Carlos A. Gomez-Uribe and Neil Hunt, Netflix), 2015

Every number

  • 80%doi.org ·2015 · Share of hours streamed on Netflix that its recommender influenced, about, as the company's leaders described it in 2015.
  • 20%doi.org ·2015 · Share of hours streamed that came from search, the remainder, as described in 2015.
  • 40 rowsdoi.org ·2015 · Rows of recommendations on a Netflix home page, roughly, as shown in the paper's figure (2015).
  1. Lessons›
  2. The school›
  3. Data and machine learning
  • ·Before this: Biased data, biased predictions