eBay Launches AI Features That “Make the Entire Internet Shoppable”
Ebay this week launched two new features that it says “will make the entire internet shoppable.”
The first, Find It On eBay, is a new feature for the company’s mobile platform. It lets consumers share images from any social media platform or web browser. Users “share” the image with eBay and the mobile app will find listings of the item captured in the image or others like it.
The second is Image Search. Take a photo of something you want to buy—or use an existing photo from your camera roll—and eBay will show you listings that match the item you are looking for.
These solutions address common problems, says Steve Neola, recommendations an image search product lead for eBay.
“Have you ever seen someone wearing something you wanted to buy but you didn’t know where to get it?” he asks. “Or maybe you saw something you liked while reading your favorite blog or flipping through Pinterest but you didn’t know where you could buy it, let alone how to describe it in words?”
The features sift through more than 1.1 billion listings on eBay.
“Find It On eBay and Image Search open up new ways to discover unique and fun items that wouldn’t be possible with just using words,” says Ben Klein, eBay’s computer vision research lead.
Leveraging advances in computer vision and deep learning, eBay utilizes a model called a convolutional neural network to process the images.
“The output of the model gives us a representation of the your image that we can use to compare to the images of the live listings on eBay,” explains Max Manco, computer vision engineer lead for eBay. “Then, we rank the items based on visual similarity and use our open-source Kubernetes platform to quickly bring these results to you, wherever you are in the world.
The idea for Image Search was developed by a small team during eBay Hack Week, an annual company-wide competition challenging technologists to innovate the ecommerce experience.