top of page

AI Case Study

Amazon makes personalised product recommendations to customers with machine learning

Amazon has leveraged machine learning to provide its customers a personalised customer experience and recommendations of products. Using a website called Scout, which collects data on their habits, demographics, and preferences, Amazon shows customers image feeds and asks shoppers to like or dislike a product. According to their feedback it then adjusts the results and thus it is even able to assist customers that do not know what they are looking for. The site is currently available for seven product categories.


Consumer Goods And Services

Retail General

Project Overview

"Scout is currently available for seven product categories: Home furniture, kitchen and dining products, women’s shoes, home décor, patio furniture, lighting, and bedding. It’s no stretch of the imagination, however, to speculate how Amazon’s engineers might use this vast amount of data to turn everyday product recommendations into a more personalized and highly specific experience on its home site.

“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,” Amazon said in a statement.

The company says that Scout is for shoppers who might not know what they want, or don’t know how to craft a written description that might yield the desired results."

Reported Results

"The resulting aesthetic at Scout 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,' according to Amazon."


Details undisclosed



Product Marketing


"Amazon is testing out a new site called Scout designed to shift customers away from traditional search — while collecting even more data on their habits, demographics, and preferences.

The company is using its proprietary machine learning technology to absorb customers’ preferences: Shoppers can like (thumbs up) or dislike (thumbs down) a product, and Amazon’s artificial intelligence responds by showing other products based on their choices. The site is currently accessible via and on the Amazon App as well."



Consumers' positive or negative feedback (thumbs up or down) to products through the website

bottom of page