Posted On: Apr 19, 2024

Amazon Personalize is excited to announce automatic training for solutions. With automatic training, developers can set a cadence for their Personalize solutions to automatically retrain using the latest data from their dataset group. This process creates a newly trained machine learning (ML) model, also known as a solution version, and maintains the relevance of Amazon Personalize recommendations for end users. 

Automatic training mitigates model drift and makes sure recommendations align with users' evolving behaviors and preferences. By default, newly created solutions will be trained automatically once every seven days. You can choose to alter the cadence of solution training via API and console or delete the solution after it has been enabled. New solution versions use the same recipe and configurations as the prior versions and incur normal training costs, but are trained on your most recent data incorporating new user interactions and the newest items. Amazon Personalize will continue training at the set cadence until you delete the solution. Existing solutions created prior to automatic training will not be impacted and will remain unchanged. Customers can choose whether to manually or automatically deploy their newly trained Solution Version to their campaigns.

Amazon Personalize enables customers to personalize their 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.