This is how Netflix stares into your soul


It's January, which means everyone is logging some extra miles on their Netflix accounts while avoiding anything and everything that will require them to: A) change out of their sweatpants and B) venture out into this bullsh** weather.

And as we all patiently await the forthcoming second seasons of House of Cards and Orange Is the New Black, the nerds over at Netflix are hard at work trying to stare directly into your soul and recommend the perfect Dark Suspenseful Gangster Drama to get you through another day of the cold and bitter gray.

Over at The Atlantic, Alexis C. Madrigal expounds on the guts and brains of the recommendations that Netflix throws at your account. The nuanced genre options. The most popular actors. The detailed subjects. The adjectives, locations, eras and other criteria that play into the stratification of the massive Netflix library.

Basically, Magrigal shows you how Netflix knows what you want before you want it. Take a few seconds to learn about the magic that helps you hibernate.

So this is the main caveat to keep in mind as we go through this data: The existence of a genre in the database doesn't precisely correspond to the number of movies that Netflix has in its vaults. All the genre's existence means is that, based on an algorithm we'll get into later, there are some movies out there that fit the description.

As the thousands of genres flicked by on my little netbook, I began to see other patterns in the data: Netflix had a defined vocabulary. The same adjectives appeared over and over. Countries of origin also showed up, as did a larger-than-expected number of noun descriptions like Westerns and Slashers. There were ways of saying where the idea for the movie came from ("Based on Real Life" "Based on Classic Literature") and where the movies were set ("Set in Edwardian Era"). Of course, there were the various time periods, as well—from the 1980s, and so on—and references to children ("For Ages 8 to 10"). [The Atlantic]

Continue Reading