eBay is introducing two AI and machine learning-powered visual search features to its mobile app: Image Search and Find It On eBay. The features are designed to help shoppers use pictures instead of words to search for eBay products.
The Image Search feature lets users upload a photo onto the app’s search bar. eBay will then display listings that are a close match or are visually similar. The Find It On eBay feature allows shoppers on any social media platform or web site to share the URL with eBay, which will then show listings matching the product.
Visual search has been around for a few years, as retailers such as Neiman Marcus and Tilly’s have paired with third-party platforms to include these features in their mobile offerings. But although Pinterest and Google Assistant have released their own image search platforms, the technology has never really taken off in retail as a means of product discovery. In acquiring visual search engine platform Corrigon in late 2016, eBay set itself up to build out its own visual search platforms, possibly paving the way for other retailers to do the same.
“We use a deep learning model called a convolutional neural network to process the images,” eBay said in a blog post. “The output of the model gives us a representation of the image that we can use to compare to the images of the live listings on eBay. Then, we rank the items based on visual similarity and use our open-source Kubernetes platform to quickly bring these results to you.”
eBay first developed the idea for Image Search with a small team during eBay Hack Week in 2015, an annual companywide competition challenging its technologists to innovate and reimagine the e-Commerce experience.
The features will be available in fall 2017. At the time of the launch, Image Search will be supported on both Android and iOS, while Find It On eBay will only be for Android devices — at least initially.