Netflix says going global has improved its personal recommendations

When Netflix launched in 130 new markets last month, not only did the video-streaming giant open its arsenal of movies and TV shows to millions more potential customers, but it also gave its recommendation engine an almighty boost, according to Carlos Gomez-Uribe, vice president of product innovation at Netflix.

The logic behind the assertion is fairly solid — the more people using the service, the more data Netflix has at its disposal. And identifying what one user may like based on something that they watch is easier if Netflix can look at other members’ habits.

[aditude-amp id="flyingcarpet" targeting='{"env":"staging","page_type":"article","post_id":1877311,"post_type":"story","post_chan":"none","tags":null,"ai":false,"category":"none","all_categories":"bots,dev,media,mobile,","session":"A"}']

Though localization is key for any company that’s going global, Netflix has had to build a new recommendation system with the world in mind.

“We saw that great stories transcend borders, and that viewers around the world have more in common than they may realize,” said Gomez-Uribe. “After an entire year, efforts from dozens of teams across the company, and intensive research, we developed and deployed a global recommendation system that will benefit Netflix members across the world.”

Without a huge global data set, Netflix’s in-country recommendations would not be quite as accurate, given that a relatively small number of local power users could influence the algorithms.

“The percentage of members from each country in this community is actually relatively small,” continued Gomez-Uribe. “So if we were relying just on the data from a single country (especially a new one with a smaller number of members), our personalized recommendations would suffer as a result. By leveraging data from across the world and countries of all sizes, our global algorithms are able to tap those insights to make recommendations […] that are more accurate and robust.”

Ultimately, this means that Netflix can lean more heavily on its machines to make recommendations, rather than manually tweaking recommendations in each country, which is surely a good thing from Netflix’s perspective. Moreover, by launching in 130 new markets, data from across the board can also be used to feed back into Netflix’s core established markets across the Americas and Europe.