Netflix Takes Global Approach to Content Recommendations

Netflix faced a challenge when it launched simultaneously in more than 100 new countries this year: how can it deliver intelligent recommendations to everyone?

The company addressed this in a blog post, where it explained a few obstacles. First, with each country’s content library being different, it can be difficult to recommend similar movies when not all exist in all libraries.

“We incorporate into each algorithm the information that members have access to different catalogs based on geography and time, for example by building upon concepts from the statistical community on handling missing data,” wrote Yves Raimond and Justin Basilico, who work on Netflix’s recommendation engine.

A second issue is cultural awareness. Even the same library worldwide will not have the same popularity in different countries—take Bollywood, for example.

“We want to make our models aware of not just where someone is logged in from but also aspects of a video such as where it is from, what language it is in, and where it is popular,” they explain.

The third challenge was language. This one is so complex that Netflix is still working to refine it.

“To support a launch of this magnitude, we examined each and every algorithm that is part of our service and began to address these challenges,” said Netflix. “Our global journey is just beginning and we look forward to making our service dramatically better over time.”