After a long refinement process, Netflix finally released its first “global” recommendation system in December.
The system takes dozens of algorithms into account, and compares you with similar users in the more than 190 countries where Netflix’s service is available.
“If one member in this tiny island expresses an interest for anime, then we’re able to map that person to the global anime community,” Carlos Gomez-Uribe, VP of product innovation at Netflix, told Tech Insider in February.
And Netflix thinks it’s worth a lot of money: one billion dollars per year, in fact. In an academic paper penned by Gomez-Uribe and Netflix’s chief of product Neil Hunt, they assert that “the combined effect of personalisation and recommendations save us more than $1B per year.”
That’s a significant chunk of change considering that Netflix’s total spending on global content this year will be $5 billion.
90 seconds or bust
Why does Netflix think it’s worth so much? The short answer is because it helps them keep subscribers from cancelling. “Consumer research suggests that a typical Netflix member loses interest after perhaps 60 to 90 seconds of choosing, having reviewed 10 to 20 titles (perhaps 3 in detail) on one or two screens,” they write. “The user either finds something of interest or the risk of the user abandoning our service increases substantially.”
If Netflix only has 90 seconds to grab a subscriber’s attention, it needs to find a good show or movie fast. If people were just typing in what they wanted to see into the search bar, this would be relatively easy. But Netflix estimates that only 20% of its subscriber video choices come from search, with the other 80% being from recommendations. So it’s essential that Netflix gets this right.
The end goal of the system are “moments of truth,” when “a member starts a session and we help that member find something engaging within a few seconds, preventing abandonment of our service for an alternative entertainment option.”
In other words, Netflix believes it could lose $1 billion or more every year from subscribers quitting service if it weren’t for its personalised recommendation engine.
And that’s why Netflix thinks that its recommendation engine, however much it could be improved in the future, is already worth so much money to the company.