Saw a show that might interest you the minute you launched Netflix? That’s no accident. Streaming services aren’t just online video repositories anymore, here’s what Netflix is cooking up behind the scenes to get you hooked.
Saw a show that might interest you the minute you launched Netflix? That’s no accident. Streaming services aren’t just online video repositories anymore, here’s what Netflix is cooking up behind the scenes to get you hooked.
Netflix everywhere, for everyone
A personal Netflix for everyone.
LOOKING BEYOND GEOGRAPHY
When Netflix finally launched globally in January to the hashtag #NetflixEverywhere, it wasn’t just its geographic reach that changed. The company also tweaked its recommendation algorithm to suit a global audience, dispensing with the previous country-specific model in favor of one that grouped users in so-called taste communities. Localized recommendations were sorely lacking from the outset because of a lack of data in new countries, so Netflix needed a new way to offer the best shows to new users. The solution was to connect users to others with similar tastes in other countries, by way of unique taste profiles curated based on individual watching behavior.
ALL ABOUT THE TAGS
But how does Netflix know that you like the same type of shows as someone living on the other side of the world? It does this by associating individual titles with specific tags, courtesy of an army of taggers whose sole job is to watch content and assign tags to them. These tags range from the staid to the outlandish, and include hilarious descriptors like “sentimental movies about horses” and “Mexican sexy comedies”. Watch enough of a certain genre or label, and you’ll get more similar recommendations. And if Netflix sees that you’ve the same tastes as a certain other user, it will cull insights from their viewing habits and factor that into the recommendations it makes for you.
YOUR OWN NETFLIX
Netflix personalizes your homepage as well, which means that even different profiles in the same Netflix account will showcase different titles. Netflix constantly stresses that it has only 60 to 90 seconds to capture your attention from the time you begin browsing, so it works hard to surface shows that you’re more likely to watch. This is important because Netflix views itself as competing with other activities for your time, and it is doing all it can to capture your attention. This requires a fine balancing act, and the ideal outcome is a homepage tailored to your tastes, but which still allows for exploration of the catalog. It does this by curating titles for individual home page rows, each of which are intended to showcase different aspects of the recommendation engine. Machine learning algorithms play a role here, and the videos in a single row typically come from a single algorithm.
REALISM 2.0
The screen is no longer the last word on digital entertainment experience. As hardware resolution wars stabilize, color, brightness and contrast become the new standard in quality and content creators like Netflix have already started to take the next step.
HELL’S KITCHEN REMADE
Matt Murdock’s eyes were two pinpricks of light in the darkened cloister of the confessional. Set against the soft shadows of the booth, the contrast could not be more striking.
In another scene, the red and blue squad car lights pouring through the stained glass windows appeared wonderfully liquid, each individual hue and tint taking on a life of its own. Elsewhere, muzzle flashes were stunningly vivid, as if the shooter was standing right there in the same room. In some ways, Marvel’s Daredevil appears almost the perfect show to illustrate the capabilities of high dynamic range (HDR) range technology. With most of the action sequences taking place in the shadows, twilight in Hell’s Kitchen is rendered more expressive, with neon signs – a blood red cross at one point – quite literally jumping off screen. Suddenly, you notice all the small details – light glinting off metallic briefcases hauled along by criminals on the run, or the twinkle of stolen diamonds strewn on the floor.
Other titles in Netflix’s stable of originals, like Luke Cage and Jessica Jones, have their own unique color palettes that lend themselves differently to HDR technology. Tony D’Amore, Senior Colorist for Marvel series at Deluxe points out that Luke Cage has a distinctly 70s Harlem vibe, with brown, red, and orange overtones, whereas Jessica Jones is characterized by a colder and more modern feel.
SO WHAT’S THE BIG DEAL ABOUT HDR?
In a nutshell, HDR enables a wider dynamic range in images, which in layman’s terms simply means that it is able to display a wider range of colors. This also translates into a greater difference between the darkest and lightest parts of a picture, and offers better detail at either ends of the brightness spectrum.
At a demonstration at Deluxe’s HDR grading facility in New York, D’Amore – on the line from Los Angeles – emphasized detail retention as one of the strongest selling points of HDR. A darkened street lit by neon signs appeared garish even in a standard dynamic range (SDR) picture, but one could clearly discern the lettering on the sign that read “Pawn Shop” in the HDR image.
This produces more realistic imagery that can be considered truer to life. “With HDR, it feels as if there’s really a car in the living room. Highlights are so much more nuanced now, so much brighter and so much more vivid,” says Manuel Billeter, Director of Photography for Marvel’s Iron Fist.
Ultimately, Netflix says that it wants to create the palette of tools that lets the director capture his intention in the picture and then deliver that with the highest possible fidelity to the user. HDR is merely a piece of that vision, but the more lifelike image quality it offers allows the entire production crew, including everyone from makeup artists to costume designers, to plumb new depths of creativity and expression.
BEHIND THE SCENES
The Deluxe grading facility is home to a ton of high-end hardware. This includes consoles with a mindboggling array of dials and knobs, and screens displaying complicated tone mapping data. But the star of the room is still probably the Dolby Pulsar monitor, which tops out at a whopping 4,000 nits. In comparison, most 4K monitors today are capable of just 300 nits.
All the HDR grading work is done on the Dolby panel, and colorists use what is called a color mapping unit (CMU) to analyze the color grade – this refers to Dolby Vision – and remap it back to what was originally streamed in SDR. But because the Hardware TVs that consumers have at home may range from anywhere between 600 and 1,200 nits, this mapping can scale the highlights to the brightest a particular screen can possibly display. This avoids clipping the highlights, and maximizes what each display is capable of.
Colorists can also tweak individual sections of the image to avoid scenarios where a particular subject ends up being distracting because it is too bright. If the cook is looking too luminous beside the burglar dressed in black, colorists can draw a shape over him and tone things down. The opposite is possible too, and faces in shadow can be lightened. This, is the new TV.
1. PERSONALIZED VIDEO RANKER (PVR)
These rows are based on genre, with headers like “Suspenseful Movies”. This algorithm orders Netflix’s catalog according to your tastes, and the resulting order is used to select the order of videos in a particular genre and in the other rows as well.
2. TOP-N VIDEO RANKER
This algorithm identifies the best few personalized recommendations in the entire catalog for each member. It focuses on the top of the rankings, unlike PVR which looks at the ranking for the entire catalog.
3. TRENDING NOW
The Trending Now algorithm hones in on short-term trends, spanning anywhere from a few minutes to a few days. It takes into account unique personalized metrics, and teases out two types of trends – those that repeat at regular intervals, such as an uptick of romantic films around Valentine’s Day, and one-off events, like a hurricane, that drive sudden interest in documentaries around the topic.
THE NETFLIX RECOMMENDER SYSTEM
4. CONTINUE WATCHING
This is more than just a list of shows that you’re halfway through. This ranker sorts the recently viewed titles based on Netflix’s best estimate of whether you intend to resume watching, or if you’re just going to abandon the title. It considers factors such as time elapsed since viewing, whether you stopped watching in the middle, beginning, or end, or whether different titles have been viewed since.
5. BECAUSE YOU WATCHED (BYW)
Finally, the BYW row anchors its recommendations to a single video. This video-video similarity algorithm, as it is called, is an unpersonalized algorithm that generates a ranked list of videos for every video in Netflix’s entire catalog. But even though the ranking itself is not personalized, the anchor video which makes it to the homepage is, as is the subset of BYW videos recommended.
