Home icon

Amazon Personalize launches new recipes supporting larger item catalogs with lower latency

Machine Learning Blog



The article announces the general availability of two new advanced recipes in Amazon Personalize, User-Personalization-v2 and Personalized-Ranking-v2, built on the Transformers architecture to support larger item catalogs with lower latency.

Specifically, the article covers:

  • Benefits of the new recipes, including enhanced scalability, lower latency, performance optimization, returning item metadata in inference responses, and highly automated operations
  • Solution overview and steps to train a model using the new recipes and get recommendations
  • Dataset preparation, model training, and getting recommendations with the User-Personalization-v2 recipe
  • Cleanup of resources
  • Conclusion highlighting the improvements offered by the new recipes


Go to article

The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.

Related articles

Apr 4
2024
Build a news recommender application with Amazon Personalize
Feb 6
2025
Amazon Personalize now supports Internet Protocol Version 6 (IPv6)
Mar 11
2024
How VistaPrint delivers personalized product recommendations with Amazon Personalize
Jun 2
2025
Streamline personalization development: How automated ML workflows accelerate Amazon Personalize implementation

The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.