If you're feeling overwhelmed ahead of Amazon Prime Day, a new AI feature from the e-commerce giant can help you get everything you want — even the items you don't know you want to buy yet. Amazon announced this week that customers will have a more personalized shopping experience by using broad language models (LLM) to adapt to individual preferences and provide more relevant product information.
The most useful, if subtle, change is the recommendation system. The list of products under “more like this” has always been based on the current product page you’re viewing, as well as your past searches and purchases. With the updated system, you’ll see ideas for things to buy that depend on specific details from your searches. Amazon’s examples describe how you can see gift suggestions based on a holiday you’ve previously purchased gifts for or recent deals on gear for a sport you’ve historically liked to play.
The actual descriptions of recommended products will now also reflect your search history. If you include a particular attribute or adjective in your search, such as vegan food or a particular furniture color, you'll see those aspects highlighted in the product title. The goal is to help you make informed decisions without having to scroll through tons of details you're not interested in — which, on a mobile device, saves valuable screen space. Combined, you should see better products and why they're recommended right away.
Prime Plan
“If the primary LLM generates a product description that is too generic or fails to highlight key features unique to a specific customer, the evaluator LLM will flag the issue,” explained Amazon director of personalization Mihir Bhanot. “This feedback loop allows the system to continuously refine suggestions, ensuring that customers see the most accurate and informative product descriptions possible.”
This year, Amazon has been steadily rolling out new AI features for shoppers. The biggest addition is its chatbot Rufus, which uses AI to research products and recommend purchases through conversations rather than keyword searches. As with much of the rest of the Amazon shopping experience, it will now include ads, but the general idea is still to make your shopping experience specific to your interests.
In the future, Amazon wants its personalized recommendations to go beyond just your Amazon history. The company has plans to include extensions to pull data from sources like Gmail and YouTube Music that would further improve the personalization of shopping. For now, you can expect your Prime Day shopping to be a little more efficient, and the products you see recommended to be a little more like what you didn't know you were looking for.