Skip to Content
Artificial intelligence

Amazon wants to use AI to recommend you clothing — again

June 7, 2019
A screenshot of blue dresses with white polka dots on Amazon.
A screenshot of blue dresses with white polka dots on Amazon.Screenshot/Amazon

StyleSnap is Amazon’s latest attempt to use machine learning to peddle fashion.

How it works: Announced at Amazon’s AI and robotics conference re:MARS 2019, the tool lets you upload photos and screenshots of clothes and accessories you like. It then uses machine-learning algorithms to match them to similar items on Amazon. Accredited "influencers" for Amazon are encouraged to get their followers on social media to use StyleSnap to take a screenshot of outfits they’ve modeled. The influencer will then earn commission on any subsequent sales.

The big picture: It’s the company’s latest crack at one of the few areas it has yet to dominate in retail. Last year, it took a different tack with the launch of a stylist assistant built into the Echo Look camera. The assistant compared two photos of you wearing different outfits and selected which looked better on the basis of fit, color combination, and current fashion trends. But reviewers found the assistant’s logic lacking, and the product never took off.

Technical difficulties: The assistant had a tougher task: it had to generate subjective opinions with relatively simple logic to back it up. With StyleSnap, Amazon may have more luck. It leans on machine learning’s biggest strength: pattern matching in images.

To have more stories like this delivered directly to your inbox, sign up for our Webby-nominated AI newsletter The Algorithm. It's free.

Deep Dive

Artificial intelligence

Why Meta’s latest large language model survived only three days online

Galactica was supposed to help scientists. Instead, it mindlessly spat out biased and incorrect nonsense.

DeepMind’s game-playing AI has beaten a 50-year-old record in computer science

The new version of AlphaZero discovered a faster way to do matrix multiplication, a core problem in computing that affects thousands of everyday computer tasks.

A bot that watched 70,000 hours of Minecraft could unlock AI’s next big thing

Online videos are a vast and untapped source of training data—and OpenAI says it has a new way to use it.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.