Everyone knows that a normal person is supposed to intake around 2,000 calories a day to stay healthy. But what does that mean? What exactly does 2,000 calories look like? To help viewers struggling to comprehend exactly what 2,000 calories looks like, Business Insider put together this new video demonstrating how much pizza, burgers, bananas, and other food items equates 2,000 calories. Obviously, a balanced diet of 2,000 calories is important.
The visual cortex takes up 30% of the human brain, so people naturally process images 60,000 times faster than text. As a result, we’re all guilty of judging books by their covers, which is a crucial element of Netflix’s engagement strategy.
Netflix has a seemingly unlimited supply of content, which can be a double-edged sword. That volume of content produces choice paralysis, where people have so many options that they can’t decide what to watch. They ultimately don’t watch anything, which underlines the importance of Netflix’s sophisticated recommendation algorithm. Netflix customizes everything on the homepage, right down to the title images.
“We don’t have a product. We have hundreds of millions of products because we deliver personalized experiences,” says Tony Jebara, Director of Machine Learning. “We’re looking to not just make recommendations, but have members believe in them.”
Machine learning drives Netflix’s algorithms, which play a huge role in the company’s success. By recommending the most relevant content, they increase engagement significantly, saving the company an annual $1 billion.
The algorithms dictate the personalized homepages and “top picks,” taking each subscriber’s viewing habits and preferences into consideration. The company utilizes a process called interleaving, which identifies the most promising ranking algorithms from a large set of initial ideas and then A/B tests using the pared-down algorithms. Compared with traditional A/B testing, interleaving works faster with smaller sample sizes.
“You end up kicking yourself because during the whole period of innovation, you’re not giving the best possible machine-learning algorithm to the users,” says Jebara.
Netflix used to use the generic title images, provided by studio partners. They were often scaled-down versions of DVD cover art that didn’t necessarily fit. The company has since performed tests to determine the images most likely to catch people’s limited attention. Engagement metrics include click-through rate, aggregate play duration, and what percentage of views had short durations.
Images with expressive facial emotions perform well, as do those featuring particular people. For example, Unbreakable Kimmy Schmidt got the best engagement with an image including both the titular character and fan favorite Tituss Burgess.
What performs even better are the images that are specifically selected for you.
“Let’s say Good Will Hunting is recommended. If we know someone really loves comedies because they’ve watched Zoolander and Arrested Development, they title image might have a picture of Robin Williams,” explains Jebara.
Do you watch a lot of movies with John Travolta or Uma Thurman? That factors into which Pulp Fiction title image you see.
At The Next Web’d TNW event, Jebara’s presentation included visuals. But they were the “official examples” from Netflix. I was curious, how did this factor into my own personal Netflix homepage?
As a Shameless fan, I searched for William H. Macy movies, like Fargo and Magnolia. None were available to stream, but even if they were… William H.Macy is a big enough star that he might be in the title image anyway. So I decided to focus on the filmographies of less-established cast members.
Mall is 2014 movie I’ve never heard of about disaffected suburbanites who come together in a mall following a shooting spree. Look at the difference between Mall‘s movie poster and my title image on Netflix. Guess what TV show the redhead is on.
The Netflix experience revolves storytelling, in a way.
“Storytelling is the heart of the human race,” says Jebara. “It’s how we share information, pass on our culture and teach the language. It started with cavemen drawing and now we’ve got PowerPoint.”
Netflix views title images as “the gateway to the stories” and the machine-learning algorithm serves the right ones for each user.
The post Machine learning and choice paralysis: How Netflix personalizes title images appeared first on ClickZ.Reblogged 2 hours ago from www.clickz.com
Monica Vila is co-founder of TheOnlineMom, an organization that provides technology education to families and helps moms connect with brands they can trust.
When my daughter Sam does a school project, it’s usually quite involved. This month she’s planning to create a board game to highlight the qualities of hydrogen, her assigned topic. She has all the physical tools she needs, poster board, art tools, etc.
But there are sources to go through; the giant science textbook, her school notes, the teachers requirement of consulting at least one school library book. There is MyBigCampus to check into for last minute reminders and her phone is buzzing with questions and comments from her friends also working on their assignments.
While she learns to prioritize her time with all this information coming at her, she also needs to learn to filter and process the information. Choosing which physical tools to use to create something is often easier than filtering through and choosing the important data.
So in this age of information at out fingertips, parents have one more important skill to teach their kids: how to be discerning. The sheer volume of information that is available to us through the web means that we have to develop filters to identify fact from fiction, good from not-so-good, truth from opinion. The ability to curate, which was formerly the exclusive domain of museums and art galleries, is now a hugely important talent for our kids.
So how do we go about teaching our kids this digital age skill? There are some everyday tasks that kids engage in that can become useful training grounds:
From Club Penguin to Facebook, kids are engaging each other on social networks. Even with all the protections in place to prevent them sharing personal information, they tend to “friend” people they don’t know in real life. If you can teach them to be discerning about who they meet online, it’s easier to teach them to be more skeptical about the information they come across as well.
At my daughter’s middle school, the head of technology demonstrated to kids and parents how Wikipedia can be manipulated to provide inaccurate information. Schools can be an enormous help in teaching your kids how to curate sites and know which ones to trust for the information they need.
Kids can take hundreds of pictures with their smartphones and cameras but are not very good at deleting those that don’t make the grade. Cleaning up an overloaded photo cache can be an important lesson in choosing quality over quantity. (And good training for curating family memories later in life.)
Teaching kids which links to open and which ones to avoid can thwart phishing attacks and other malware threats, and is an important step in safeguarding personal information. And knowing when to ignore links will allow them to better focus on their school work and other priorities!
So it’s time to learn the art of curating the terabytes of content humans are bombarded with on a regular basis – it’s a survival skill and one that will provide an incredibly important advantage to kids in schools and the workplace of the future.
What do you think? Are there other areas of filtering and curating that we need to teach our kids?
Listen, I get it. I guess Im technically a reporter (not sure what to call someone who covers politics and breaking Kardashian news, so well go with reporter), and I also carry around police tape just in case I need to get a story.
Viewers tuned in to ABC News on Friday morning to watch live coverage of reporter Linsey Davis reporting from a crime scene in South Carolina.
The terrifying location was where a woman had been held captive in a storage container by a sex offender.
Except that crime scene tape was just a prop to make it look like Davis was at the real scene of the crime.
CNN obtained this photo that shows the truth.