Posted On: Aug 12, 2022

Amazon Personalize now allows you to promote specific items in all users’ recommendations based on rules that align with your business goals. Amazon Personalize enables developers to improve customer engagement through personalized product and content recommendations – no ML expertise required. Personalize currently recommends relevant items for each user or similar items to a given item based on interactions and metadata information. With this launch, you can define business rules to identify items that you want to promote across your user-base. You can also control the percentage of promoted content in your recommendations. For example, E-commerce customers can use this feature to fill 20% of recommendations with items marked as “on sale”. Similarly, Video-on-Demand customers can use this feature to fill 40% of their rail/carousel with linear/live TV content. Based on your business rules and definitions, Amazon Personalize finds relevant items for promotion and distributes them within user-specific recommendations.

Configuring promotions is easy. When requesting recommendations with the AWS console or the API, define an additional filter criterion that identifies the promoted items, input the percentage of recommendations you want to use for promoted items, and you are ready to go.

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