Netflix’s prediction algorithms are driving its success
Select language to see a machine translation of this article. The original language of the Article is English and the translation is provided for your convenience.

Netflix’s prediction algorithms are driving its success

There are lots of areas in which streaming video on demand (SVOD) market leader Netflix has the edge on its competitors. Whether it’s content creation, subscription pricing, or ease of use, the company knocks almost everybody else out of the water, hands down. But there’s one area which gets less attention, and may prove to be even more powerful, than all of these things: the technology behind its predictive powers.

Netflix’s share price has appreciated by an incredible 106% year to date

graph 2606 netflix

SOURCE: Yahoo Finance

Netflix is an expert at suggesting shows that we might like to watch. It’s what lies behind the binge-watching behavior of many of its users, and what helps us encounter shows we love, but may never have watched without a nudge. This is not a simple matter of chance – Netflix has invested heavily into developing tools that will push its content out to viewers in sensible ways. That’s a necessity given the scope of Netflix’s content library, and it’s also the key ingredient in creating a service that users love.

In the company’s own words: “We want to estimate the conditional probability that a subscriber will like a film, given his or her particular viewing history, in light of the ratings data from all other subscribers. This will allow us to personalise film recommendations for each viewer.”

Netflix has this down to a fine art: 80% of all the hours streamed on its platform are funneled through this recommendation system. The actual maths behind the process is too complex to detail here – and, in any case, unnecessary – but it all centers around probability theory and the use of a statistical “offset”. The company worked incredibly hard to discover the best way to recommend movies and TV shows to people, offering a $1 million challenge in 2009, where the prize was claimable by a suggestion able to increase the system’s accuracy by 10% or more.

Given the company’s recommendation system’s success in driving viewers to compulsively watch more, it was money and time very well spent.


Dominion holds Netflix in its Global Trends Ecommerce Fund.

If you would you like to receive the Newsfeeds daily, please click here to sign up now!

Help us make this Newsfeed better by rating this article. 1 star = Poor and 5 stars = Excellent
0.0/5 rating (0 votes)

The views expressed in this article are those of the author at the date of publication and not necessarily those of Dominion Fund Management Limited. The content of this article is not intended as investment advice and will not be updated after publication. Images, video, quotations from literature and any such material which may be subject to copyright is reproduced in whole or in part in this article on the basis of Fair use as applied to news reporting and journalistic comment on events.