It’s a moment familiar to many Amazon shoppers: search or browse, and you’re presented with an overwhelming array of product choices. Sometimes, you freeze.
But we all know how to click on a button to vote up or down what we like or don’t like. That’s the simple concept behind Scout, a new feature Amazon has quietly, but openly, introduced for shoppers in a number of categories. It filters recommendations based on what shoppers like or don’t.
The Scout page on Amazon shows images of products ranging from coffee tables to shoes in seven categories: furniture, home decor, lighting, kitchen & dining, patio, bedding, and women’s shoes. Instructions at the top of the page state simply, “Welcome to SCOUT. ‘Like’ or ‘dislike’ for instant recommendations.” Product images are represented on tiles, and clicking the thumbs-up or thumbs-down icon flips some of the tiles to reveal new choices, apparently narrowing options by characteristics the “liked” items have in common.
Scout-enabled categories can also be accessed from individual product pages, wherever a “SCOUT Style explorer” gray bar appears.
“This is a new way to shop, allowing customers to browse millions of items and quickly refine the selection based solely on visual attributes,” an Amazon spokesperson said in a statement to CNBC, which first reported the test. “Amazon uses imagery from across its robust selection to extract thousands of visual attributes for showing customers a variety of items so they can select their preferences as they go.”
The Amazon spokesperson also told CNBC the machine-learning based Scout engine is being tested in the Amazon App for home furnishings and women’s shoes.
Which products are next? A series of images at the bottom of the Scout page — from plush toys to purses — only hint, under a headline of “Watch this space! More categories coming soon.”