I am an avid television user and like the majority of people, I use streaming services to fuel my addiction like Netflix, Hulu, Amazon Prime etc. I prefer streaming services because for one, the subscriptions for streaming services are much, MUCH cheaper than cable and secondly because I can access any movie or TV show on the comfort of my own time. However, the thing I appreciate a lot about these services is their ability to recommend good movies or TV that I would like, based off the films/ TV I have watched in the past or based off of recommendations. Even though this is a small factor, this tool really helps viewers find interesting content that they want to watch.
There is so much media content out there now but how do streaming services effectively recommend content you would actually like to watch? One thing that Netflix and Hulu both do well is that they are able to personalize your account to make content that you are interested in easier to find and view. Netflix started this idea that viewers should have personalized profiles that recommended content based off their past likes and ratings. Eventually, Hulu developed to offer its viewers personalized profiles too.
With Walt Disney Co saying that it will take full control of the Hulu service, Hulu has become the largest competitor of Netflix today. But Hulu’s recommendation model is rather primitive or simple compared to Netflix’s recommendation model . Content suggestions on Hulu are reportedly based on account-level information such as zip code data, etc, and can be further honed based on which household member is viewing the service at that time, previous viewing habits, as well as additional information that Hulu incorporates into its decision engine. My personal observation has been that the suggestions Hulu offers are usually in the same genre of the movie or TV show we just watched. So if you watch shows about female empowerment or adult animation, that is all you get even if the shows aren’t of the same quality.
However, Netflix’s model is a little more complex. Netflix is better able to recommend movies that are related to the title and can considered of the same quality. As a film major, I find this tool particularly effective because Netflix is particularly good at finding films or TV shows that I am interested in or those that will help me in my research and studies. But how does Netflix do this?
On average a person who uses Netflix views 40 to 50 titles before they pick what they’re going to watch. Perhaps the biggest personalisation in Netflix is the rows of shows a user is presented with. These are largely based on our watching history on the subscription platform.
Netflix is always testing and scheming. Each time you click play, pause, or – heaven forfend – stop watching TV altogether, it gathering data on your preferences. Spread across more than 300 million user profiles, this is a colossal amount of information. And it all feeds back into what you see when you next look for something to watch.
Todd Yellin, the vice president of product who has been at the company for ten years, explains that data informs everything Netflix does. “If you click play nowadays in the streaming world, it tells volumes more information that is a lot less superficial than getting someone’s gender and age,” he says.
Netflix creates multiple different landing cards for each of its titles and no user will be shown exactly the same combination rows, but Netflix will occasionally throw in new shows and types of shows it thinks a person may be interested in.
Additionally, Netflix runs 250 A/B tests each year. These tests present users with two slightly different experiences to see how they respond, varying from changes to the way the Netflix player looks or the mechanisms by which people find shows.
Netflix customises its recommendations based on when you’re watching. Netflix may show you shorter programmes, or ones you’re halfway through, when you login late at night and may not be looking to watch an entire show from scratch.
Another function of Netflix is that if you start watching a series but don’t get to the end of it, Netflix’s algorithm will occasionally resurface the unfinished show in a bid to tempt you back onboard.
Hence we can all see our personalized Netflix account takes shape as a consequences of every decision we make on the app.
However, something Netflix used to do in the past that I really miss is that they asked viewers to rank the film according to rank films. As a Netflix user, I was able to able to use this data to discern the likeability of the show and whether I should watch it. I recognize that the obvious problem with this is that different people have different tastes in film and just because a film is popular, doesn’t make what can be academically or technically considered a good film.
Netflix replaced this function for ‘data’ that now shows the match in percentage to your ‘profile.’ For example, because I watch shows like ‘House of Cards’ and ‘Orange is The New Black,’ the television show ‘Designated Survivor’ was recommended at a 98% percent match for me.
One thing I find cool about Netflix, is that it doesn’t include age or gender in its recommendation system as it doesn’t believe they’re useful. Taking age and gender out of the equation is what makes for Netflix’s highly personalizabable profiles, since you aren’t limited to what you can find and explore. My profile is strongly based off of what I like as an individual and acts as my independent assertion of my taste in film, different from other girls or from people my age.
Netflix collects and stores this huge amount of data and uses this data to target audiences and advertise products and other TV shows. With the personalization of profiles and the data collection from its viewers, Netflix is able to target its audience to advertise TV shows and movies that the viewer might personally be interested in (regardless of gender or age).
However, one of the major drawbacks with Netflix’s collection of data is that there have been complaints that Netflix tends to include racial profiling when it comes to recommending films to viewers, sometimes even misleading viewers.
For example, viewers who watch sitcoms with a full black cast are recommended to watch media content with black casts. However, Netflix began using this weird marketing ploy where they began to use landing cards with black people to advertise TV shows with full white casts. This is essentially false advertising and it is quite irritating because the viewer ends up being duped into watching something completely different from what he/ she was expecting.
Hence we begin to see how our personalized Netflix account takes shape as a consequences of every decision we make on the app. The data collected by the app is owned by Netflix to make the app better for us, which is a good thing as we are able to enjoy our unique experience and find similar content to what we like. However how this data is being used needs to be reconsidered to ensure the ethics of it all because data like this can be used to segregate people according to what they watch on TV, and streaming company giants like Netflix should be especially careful about how they use their collected data.