Fashion trends are diverse, fleeting and often hard to describe. When faced with a waiting search bar, shoppers can experience a sense of writer’s block—even if they’ve seen their desired look on a favorite infleuncer.
The shape of a neckline; the length of a skirt; the name for a specific dip-dye pattern that’s been dominating Instagram feeds. While consumers find these details compelling, coming up with the right search terms can be a slog that yields disappointing results.
Amazon’s StyleSnap, however, allows shoppers to show (rather than tell) the marketplace what they’re looking for, the company said in a statement.
Using a photo or a screenshot of a desired outfit or garment, the program provides shoppers with recommendations of similar items available for sale on the site.
To use the feature, users click the camera icon in the upper right corner of the Amazon app and select the StyleSnap option. From there, they can upload their own photo (perhaps taken while shopping in a store or a friend’s closet) or a screenshot of their favorite style blogger. Amazon’s recommended styles can be filtered by size, price range and customer reviews.
The feature relies on computer vision and “deep learning,” a subset of machine learning inspired by the neural network of the human brain. The artificial neurons can be trained, through extensive data input, to recognize the features that differentiate a range of similar products. By feeding the system thousands of reference images, StyleSnap’s deep learning technology has learned to pick up on nuance—like the difference between a maxi skirt and an accordion skirt, for example.
The feature can also filter out the noise that often accompanies a photo shared on social media, focusing in on the apparel instead of the iced coffee on the table, or the backdrop of a bright blue sky.
The e-commerce firm noted that style bloggers who join its Amazon Influencer Program make money when one of their screenshot outfits inspires someone to buy.
StyleSnap is the latest of Amazon’s manifold efforts to win the loyalty of female shoppers. In May, the company announced an influencer collaboration program called The Drop, wherein globally recognized fashion stars design limited-edition collections which are sold on Amazon within a 30-hour window. The first collection, designed with influencer Paola Alberdi, dropped on June 5.
StyleSnap is Amazon’s answer to the ramp up of visual search tools being created for online commerce.
In March, Google rolled out shoppable ads that target consumers who view image search results on its search engine.
In January, Amy Vener, Pinterest’s leader of the retail vertical strategy described smartphone cameras as “your next keyboard,” adding that “visual search is where it’s at for retail.” The company debuted Pinterest Lens, which matches user-photographed products with visually similar results, in 2017, and has steadily added new facets to the feature to make search more efficient.
Donde, a visual search startup that’s helped Forever 21 boost average order values by 20 percent, raised $6.5 million in February to “help merchants think like their customers,” CEO Lia Zakay said at the time.
Amazon’s StyleSnap feature also appears to be an evolution of a concept that the e-commerce company debuted last fall with Snapchat allowing the social platform’s users to search Amazon’s marketplace using the Snapchat camera.
“We are highly innovative and customer-obsessed, and we will continue to create new experiences for customers to discover the products they want and love,” said Jeff Wilke, Amazon’s consumer worldwide CEO.
“We are incredibly excited about StyleSnap and how it enables our customers to shop visually for Fashion on Amazon,” he added.