Is Netflix stalking you?

Humans have the attention span of a goldfish, giving companies like Netflix just a few seconds to woe you before it loses you to a competing service or something other activity. Netflix wants to grab your attention say like a new boyfriend, but does it do this without spamming you with texts or calls?

Your answer is — Image or Artwork Personalisation

Getting a little technical here, Netflix relies heavy on batch machine learning approaches information gathered by algorithms that reflect A/B testing. It considers user-specific factors to emphasis size themes and create and artwork FOR YOU like

1. Viewing day, time, location and device
2. Platform searches like key words and number of searches
3. Whether content was paused, rewound, re-watched or fast forwarded. (It even saves screenshots of when the show was paused, when the user left the show, and when the user watches a scene more than once)
4. Content abandonment times and rates
5. Browsing and scrolling behaviour

Netflix’s Riverdale Thumbnails

Okay, Okay I know this was too much so imagine you are someone who watches more thrillers or mysteries you will see a thumbnail with Archie, Betty, and Veronica looking at you all intense emoting suspense. Now imagine me as someone who watches more romance and high-school drama, actually scrap that KNOW ME as someone who loves it — I’m all about the notebook, the vow, and letters to Julliet. But yes so, I will get a thumbnail of Riverdale with Archie, Betty, and Veronica smiling and looking all cute.

So, it’s the same show, same characters but different thumbnails. This is cause Netflix got information about your keyword, content you’ve watched, how you’ve watched, abandoned, and browsed. So, I guess we could call Netflix your Entertainment Stalker, maybe?

So how does Netflix do it?
Analyzing, choosing, deciding, and delivering these thumbnails.

So think about the show Stranger Things, it has about 86,000 static video frames in a 1-hour episode, with 8 episodes in each season and 3 seasons — that’s like over 2 million static video frames to analyze from. Now I get Mike and Eleven are cute and all, cause like Millie Bobby Brown… DIVA but it’s a bit much for Netflix’s team to analyze and choose from too.

Netflix’s Stranger Things Riverdale

So what Netflix does is, it turns to Artwork Visual Analysis. It’s a collection of tools and algorithms designed to surface high-quality imagery from the videos to predict which merchandise will resonate most with individual users based on their age and general preferences.

AVA uses computer vision to scan each frame of every title to analyze visual data to drive image selection that meet Netflix’s aesthetic, creative, and diversity objectives requirement for Netflix’s user interface. These include —
— Composition Metadata: heuristic characteristics that make up the images overall aesthetic
— Contextual Metadata: facial expressions, objects

So here we are

With each passing day, Netflix provides users with a more personalized and improved experience. Using algorithms like aesthetic visual analysis to create thumbnails a user would appreciate. Also, through online machine learning Netflix decides what to recommend based on their recent watch history.

Is this right? Maybe.
Is this fair? I don’t know.
But do I like the benefits of it? Absolutely.

So Netflix knows of all your viewing likes and dislikes without you knowing exactly, is that the new age stalking?