Amazon launches Scout, a machine learning-powered visual shopping tool

Amazon is experimenting with a new tool called Scout designed to help shoppers better figure out what they want to buy in a more visual fashion, according to a report from CNBC, which first spotted Scout live on Amazon’s site. Using a combination of imagery, a thumbs up and down voting mechanism, and machine learning technology, Scout offers an almost Pinterest-like way of browsing Amazon products, then refining recommendations through user input.

Currently, the site lets you search for furniture, kitchen, dining products, home décor, patio items, lighting, and bedding, as well as women’s shoes. In time, Amazon will add more products like clothing and handbags, it said.

While Amazon.com today has just about any product you could want, finding items you like when you only have a vague idea of what you want can be more difficult. For example, if you’re looking for a dresser, or a new comforter, or deck chairs, you’re often stuck scrolling down through a long list of matching results that aren’t at all customized to your particular tastes.

For this reason, shoppers tend to find themselves heading to other more “inspirational” sites, like Pinterest or Houzz, for example.

Scout aims to help customers narrow down their choices more quickly.

Specifically, it focuses on solving two dilemmas, an Amazon spokesperson said: “I don’t know what I want, but I’ll know it when I see it” and “I know what I want, but I don’t know what it’s called.”

“This is a new way to shop, allowing customers to browse millions of items and quickly refine the selection based solely on visual attributes,” the spokesperson noted. “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. This innovative shopping experience is powered by machine learning. The result is a beautiful and inspirational image feed, which gives customers the ability to explore a wide range of products in a playful and personalized manner with just a few clicks,” they added.

This isn’t Amazon’s first go at trying to solve its discoverability problems or add elements of personalization to product hunting. The retailer had previously launched a site feature called “Interesting Finds,” which features a curated selection of products under dozens of top level categories like clothing, toys, gadgets, travel, workspace, smart home, pets, and more. As you “heart” (like) items in this visual storefront, Amazon then creates a personalized group of suggestions called “My Mix.”

But Interesting Finds today is more about serendipitous discovery – not a directed search where you want to refine the results to your personal tastes.

While Amazon hadn’t publicly announced Scout, some Amazon shoppers were happening upon it when browsing specific products. There, they’d see a link to “Scout Style Explorer” which would take them over to the new tool, CNBC said.

The site isn’t its own URL, but rather a subsection of Amazon.com, on amazon.com/scout.

The retailer says it’s live now on Amazon’s website and in Amazon App.

Read more: https://techcrunch.com/2018/09/19/amazon-launches-scout-a-machine-learning-powered-visual-shopping-tool/

Leave a Reply