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?
Words to know
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 rows
doi.org ·2015 · Rows of recommendations on a Netflix home page, roughly, as shown in the paper's figure (2015).