If you’re feeling overwhelmed ahead of Amazon Prime Day, a new AI feature from the e-commerce giant may help you score everything you want, even the items you don’t yet know you want to buy. Amazon announced this week that customers will have a more personalized experience when shopping by employing large language models (LLMs) to match individual preferences and provide more relevant product information.
The most useful, though 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 looking at, as well as your previous searches and purchases. With the updated system, you’ll see ideas for things to buy that rely on specific details of your searches. Amazon’s examples describe how you might see gift suggestions based on a holiday that you’ve bought gifts for previously or recent deals on gear for a sport your history suggests you like to play.
The actual descriptions of those recommended products will also now reflect your search history. A particular attribute or adjective you include in your search, such as vegan food or a particular color of furniture, will translate to seeing those aspects highlighted in the title of the product. The point is to help you make informed decisions without having to scroll through tons of details you don’t care about, which, on a mobile device, saves valuable screen space. Combined, you should see better products and why they are recommended immediately.
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,” Amazon director of personalization Mihir Bhanot explained. “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 deploying new AI features for shoppers. The biggest addition is its Rufus chatbot, which uses AI to research products and recommend purchases through conversations rather than keyword searches. As with much of the rest of Amazon’s shopping experience, that will now include advertisements, but the general idea is still making your shopping experience specific to your interests.
In the future, Amazon wants its customized advice to pull from more than just your Amazon history. The company has plans for extensions to pull data from sources like Gmail and YouTube Music that would further enhance shopping personalization. For now, you can expect your Prime Day to be a little more efficient and the products you see recommended a little more like exactly what you didn’t know you were searching for.