Amazon Personalize now creates themes for recommendations using generative AI

Amazon Personalize is excited to announce Content Generator, a new generative AI powered capability that makes recommendations more compelling by identifying thematic connections between recommended items. Content Generator will assist customers in crafting taglines to create a more engaging browsing experience.

Amazon Personalize generates recommendations for your users at scale. Companies typically display these recommendations with generic taglines such as “People who bought this also bought” or “Because you watched” on product pages or marketing campaigns. Amazon Personalize Content Generator uses large language models (LLMs) to generate a snippet of text that describes the thematic similarity between recommended items. These can be incorporated into titles for recommendation carousels or email subject lines. For example, Content Generator enables you to generate a theme like “Rise and shine” for a collection of breakfast foods, replacing a more generic title.

Getting started with Amazon Personalize Content Generator is easy. Customers can enable theme generation in batch inference jobs either via the API or AWS console. Furthering our innovation, Amazon Personalize also launched Langchain integration and returning metadata in inference reponse to improve your generative AI workflow. Learn more about how to use Amazon Personalize and generative AI to enhance your customer experience in our blog.

Amazon Personalize enables customers to personalize your website, app, ads, emails, and more, using the same machine learning technology used by Amazon, without requiring any prior ML experience. To get started with Amazon Personalize, visit our documentation.