You will be redirected back to your article in seconds

How Amazon Recommends Movies on Prime Video

Amazon worldwide consumer CEO Jeff Wilke gave attendees of the company’s Re:Mars conference a look behind the curtain of content recommendation for Prime Video Wednesday, explaining how the company improved its recommendation algorithms to become twice as good in recommending movies, TV shows and more.

“Product discovery was heavily based on human curation and bestsellers when we started,” Wilke said. When Amazon started to sell books online, it began with a relatively small inventory, which made it easy enough to recommend bestsellers and more to its audience.

However, that approach didn’t account for special interest groups, with Wilke calling out books for mushroom hunters as one of the areas that fell by the wayside. To include this long tail, Amazon developed collaborative filtering, which to this day powers some of the product recommendations made on its side — think customers who bought this product also bought these other products.

collaborative filtering at Amazon Prime Video
CREDIT: Janko Roettgers / Variety

As Amazon’s computing resources grew, the company wanted to use some of those smarts to power its recommendations by more advanced technologies. In 2012, Amazon engineers began to develop and test new technologies to recommend products on its site. But approaches that proved promising, including neural networks and other types of machine learning, didn’t exactly work as expected.

deep learning test for Amazon Prime Video
CREDIT: Janko Roettgers / Variety

In fact, many of these AI approaches not only performed worse than collaborative filtering, but even than the company’s original approach of human curation and bestseller lists. Wilke said that Amazon’s engineers decided to take a look inside of the black box of machine learning to figure out what was going on.

movie recommendations on Amazon
CREDIT: Janko Roettgers / Variety

Turns out that Amazon had inadvertently trained its algorithms to recommend safe bets. In the case of Prime Video, these were classic movies that were well-regarded. Think the “Breakfast Club,” or “Casablanca.” But while these movies had high ratings with audiences and critics alike, they weren’t exactly what consumers wanted to watch during their next movie night.

amazon prime video filtering algorithms
CREDIT: Janko Roettgers / Variety

That’s why Amazon’s engineers tweaked its content recommendation algorithms, which are now trained on Amazon’s entire catalog, but apply this knowledge on new titles to recommend the latest releases. The result was a 2x improvement over collaborative filtering, Wilke said.

Wilke explained that Amazon was applying the same kind of approach on other areas of shopping to account for changing tastes as well as shopping habits. “People do not shop the way they did in 1995 when Amazon started. They do not shop like in 2015,” he said.

He added that all of this was powered by Amazon’s own cloud computing, and other resources the company had because of its DNA. Said Wilke: “Amazon has been a technology company from the start.”

More Digital

  • Cameo

    Celebrity Video Greetings Service Cameo Raises $50 Million

    Cameo, a service that works with celebrities to sell personalized video greetings to fans, has raised a $50 million Series B round of funding led by Kleiner Perkins. The Chernin Group, Spark Ventures, Bain Capital and Lightspeeed Venture Partners participated in the funding as well. Cameo wants to use the cash infusion to grow both [...]

  • Gena Konstantinakos - Topic

    Topic Hires Viceland's Gena Konstantinakos as VP, Development and Video Programming

    Topic, First Look Media’s entertainment studio and digital destination for original content, hired veteran producer Gena Konstantinakos as VP, development and video programming. Konstantinakos hails from Vice Media’s Viceland cable channel, where she was executive producer, development and current series. At Topic, she reports to Ryan Chanatry, general manager of Topic. Konstantinakos is tasked with [...]

  • Martin Kon - YouTube

    YouTube Hires Consultant Martin Kon as VP of Strategy

    Google’s YouTube tapped Martin Kon, who has worked as a tech, media, and telecoms consultant for more than two decades, as VP of strategy. Kon, based at YouTube’s headquarters in San Bruno, Calif., reports to chief business officer Robert Kyncl. Kon will work with YouTube senior execs to help formulate the long-term vision of the [...]

  • Sonos One

    Sonos Sues Competitor Bluesound for Patent Infringement

    Smart speaker maker Sonos has sued Lenbrook Industries, the company behind the audio brand Bluesound, for patent infringement. It’s the second such lawsuit from Sonos against a competitor, which has also been using its patents to gain concessions from the makers of voice assistants. In the lawsuit filed late last week in a California court, [...]

  • tubi tv roku

    Ad-Supported Video Service Tubi Tops 20 Million Monthly Active Users

    Ad-supported video service Tubi broke its own audience records in May: Tubi, which positions itself as a free alternative to Netflix, surpassed 20 million monthly active users last month, the company said Monday. The service’s users viewed more than 94 million hours of programming in May, according to Tubi, which also claimed to have brought [...]

  • First Media - Chris Athanassopoulos, Jocelyn

    First Media Names Chris Athanassopoulos CFO, Jocelyn Johnson as SVP of Brand

    First Media, the media company focused on millennial women audiences whose brands include BabyFirst TV, announced two new members of its executive team as it eyes expansion in 2019. Chris Athanassopoulos, previously Twentieth Century Fox’s VP finance for worldwide TV distribution, has joined First Media as its chief finance officer. (First Media’s previous CFO, Karl [...]

More From Our Brands

Access exclusive content