eBay Launches New Image-Based Search Tools for its Apps

Earlier this fall, eBay announced that it had launched two new image-based search tools — Image Search, Find It On eBay — for its mobile apps. The artificial intelligence (AI)-powered features enable shoppers to use pictures instead of words to search eBay’s catalog of 1.1 billion items.

In this interview with Giri Iyengar, head of computer vision, eBay, he discusses how the tools work, as well as the impact the retailer believes it will have on its customers’ shopping experiences.

Giri Iyengar, Head of Computer Vision, eBay

Total Retail: Can you tell us about Image Search, and why it's a valuable feature for eBay's customers?
Giri Iyengar: Have you ever seen something at a store and wondered if you could get it cheaper online? Or maybe you saw something you liked while reading your favorite blog but didn't know where you could buy it, let alone how to describe it in words? To help people solve the challenge of spending hours scouring stores or the web for certain items, we applied artificial intelligence and machine learning technology to create new ways for consumers to find what they want, for the price they want it. These new experiences allow customers to shop eBay through images no matter how hard the item is to describe — whether they’re images you take yourself out in the world or if you find inspiration online.

With Image Search, you can take a photo of something you want to buy or use an existing photo from your camera roll and put it into the eBay Search bar on our native apps. Then, we’ll show you listings that match the item you're looking for.

TR: The same question applies to Find It On eBay.
GI: We developed Find It On eBay to make online shopping convenient. Find It On eBay is a new feature in our eBay app and mobile platform that lets you share images from any social platform or web browser. All you have to do is “share” the image with eBay and our mobile app will find listings of the item in that image or others like it.

TR: Why has eBay chosen to invest in AI and machine learning technology?
GI: At eBay, we're taking an AI-first approach by integrating AI across our platform. Advancements in AI and machine learning technology are gaining momentum and seeing more progress than ever before. We've been experimenting with these cutting-edge technologies to create more personalized experiences and bring customers what they want, at the best price. Our rich set of data on more than 1 billion items puts us at a technological advantage. Combining AI with eBay’s breadth of inventory and unique selection will enable us to create a more personal shopping experience for virtually anyone that owns a mobile phone.

TR: What are the primary benefits that eBay hopes to realize from the launch of these new tools on its mobile apps?
GI: The rollout of our new Image Search and Find It On eBay experiences are only an entry point for what the future of image-powered shopping will look like. By creating this technology and experimenting early, we're enabling ourselves to quickly evolve and adapt our technology. As people continue to use Image Search, eBay will be able to surface even richer results, helping shoppers find their perfect item, at the perfect price. While still early, we think we will reach a point where people can seamlessly shop their world and the entire internet on eBay — no matter how hard the item is to describe.

This is particularly relevant during the holiday season. As shoppers use the newly rolled out technology to search with pictures, Find It On eBay and Image Search will get smarter, learn and deliver results. The holiday season will be a good test of the new products. Our shoppers can use Find It On eBay and Image Search to find First Minute deals on items that they love, and our technology will continue to improve.

TR: How has eBay's business evolved to account for changing customer behaviors, such as the increased use of mobile for shopping?GI: Consumer shopping habits are shifting, which is resulting in more of an emphasis on the shopping experience and personalization. We recognize that in order to survive, retailers need to evolve to meet the changing needs of customers. For eBay, the rich set of user-generated images and item data we’ve accumulated through the years puts us at a technological advantage. While still early, we think we will reach a point where people can seamlessly shop their world and the entire internet on eBay.

TR: What has the early customer feedback been for these new tools?
GI: The early consumer feedback has two components to it: one, we see that buyers are clearly using the Image Search technology to shop for the three categories which we expected the most impact (fashion, collectibles, and home & garden) and two, they're interested in comparison shopping for the best deals based on the images we're seeing being sent to the search services from other e-commerce platforms.

In addition, we've seen a strong following of the technology amongst sellers, who are using it to source items for sale, get pricing information and validate their own listings.