Amazon Scout Uses Machine Learning To Show Shoppers Personalized Products

Amazon is working on a website for consumers who aren’t sure what they want to purchase and want automated help.

CNBC, citing Amazon, reported the service dubbed Scout queries consumers about whether they like or don’t like a product and then shows other products based on how they answer. If you give thumbs up to, say, a pink sweater with bell sleeves, you may be shown more tops with that style.  The test is aimed at answering critics who CNBC reported contend Amazon is a great place to make a purchase, but for browsing — not so much. According to the report, Scout works for a slew of product categories including home furniture, kitchen and dining, women’s shoes, home decor, patio furniture, lighting and bedding. Clothing and handbags are being added to Scout soon, reported CNBC. Customers like or dislike the image by giving it a thumbs up or down and then get tailored recommendations in real time to help them find the products they like best. The new feature is powered by machine learning.

“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 an emailed statement to CNBC. “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.” CNBC noted that Amazon hasn’t been promoting Scout, but some consumers may have already found it when shopping in certain categories. The Amazon spokesperson went on to say that “Scout is aiming to free people from the need to use words to describe what they’re looking for when shopping in highly visual categories,” reported CNBC.

The new feature comes at a time when Amazon is becoming more important to marketers looking to promote their products. According to market research firm eMarketer, Amazon is forecast to reach the number three spot among sellers of digital ads in the U.S. this year.