How do platforms like YouTube and Netflix recommend videos to watch? This is largely based on algorithms in which it looks at the videos you’ve watched in the past and tries to recommend other videos and movies that it thinks are in a similar vein. How accurate are these recommendations? Sometimes they can be pretty spot-on, but are they necessarily the best way to go about it?

Maybe not, because it looks like Netflix has decided to start testing out human-curated content in a feature called “Collections”. In a way, this will be similar to the current recommendation system where it recommends users new shows to watch. However, the videos are grouped into different categories such as “Let’s Keep It Light” or “Dark & Devious TV Shows” or “Prizewinning Movie Picks”.

This sounds similar to other recommendation systems used by other platforms like Spotify, where instead of being genre-based, it is mood/category based. Netflix has confirmed that they are testing out the feature, although the company stopped short of saying if it will become a permanent thing.

In a statement made to TechCrunch, a spokesperson said, “We’re always looking for new ways to connect our fans with titles we think they’ll love, so we’re testing out a new way to curate Netflix titles into collections on the Netflix iOS app. Our tests generally vary in how long they run for and in which countries they run in, and they may or may not become permanent features on our service.”

Filed in General. Read more about and . Source: techcrunch