Artificial IntelligenceCryptocurrencyMetaverseCybersecurityTech Forward

Netflix says Geography, Age, and Gender Are ‘Garbage’ for Predicting Taste

March 27, 2016, 7:28 PM UTC

Netflix (NFLX) rolled out to 130 new countries earlier this year, and you might expect that it began carefully tailoring its offerings for each of them, or at least for various regions. But as a new Wired feature reveals, that couldn’t be further from the truth—Netflix uses one predictive algorithm worldwide, and it treats demographic data as almost irrelevant.

Get Data Sheet, Fortune’s technology newsletter.

“Geography, age, and gender? We put that in the garbage heap,” VP of product Todd Yellin said. Instead, viewers are grouped into “clusters” almost exclusively by common taste, and their Netflix homepages highlight the relatively small slice of content that matches their taste profile. Those profiles could be the same for someone in New Orleans as someone in New Delhi (though they would likely have access to very different libraries).

Netflix (NFLX) seems to have discovered (or built on) a powerful insight from sociology and psychology: That in general, the variation within any population group is much wider than the collective difference between any two groups. So if you want to, say, get someone to stream more of your content, you’re better off leveraging what you know about similar individuals in completely different demographic groups, than trying to cater to broad generalizations.

As an example, Wired shares that 90% of Netflix’s total anime streaming volume comes from outside Japan. That’s because how much you like anime is determined less by your nationality than by (pardon me) how big of a nerd you are.

There’s a huge, crucial lesson here for other businesses—and perhaps a slightly scary reality for consumers. In the era of big data, consumer profiling can’t rely on broad categories like race or location. To target the customers who want what you’re offering, you have to get past the surface and see what really makes them tick.