AWS Clean Rooms ML is now generally available

Today, AWS announces the general availability of AWS Clean Rooms ML, which helps companies apply machine learning (ML) to generate predictive insights in a data collaboration without sharing their raw data with their partners. This capability launches with an ML model that helps companies create lookalike segments. With AWS Clean Rooms ML lookalike modeling, you can train your own custom model using your data and invite your partners to bring a small sample of their records to a collaboration to generate an expanded set of similar records while protecting the underlying data with purpose-built privacy controls. AWS Clean Rooms ML enables collaborative ML use cases including those for healthcare, financial services, and travel and hospitality.

Organizations across industries strive to use their data to unlock insights that help acquire customers and improve business processes while protecting consumer privacy and intellectual property. AWS Clean Rooms ML lookalike modeling helps you collaborate with your partners to create ML-powered lookalike segments without having to share or exchange sensitive data. For example, a consumer brand can now collaborate with a media publisher to find new customers that are similar to their existing, best customers, without having to share or upload their sensitive data. Similarly, healthcare customers can recruit participants for clinical trials or medical research using a seed list of participants with the desired characteristics. With AWS Clean Rooms ML, you retain full control and ownership of your trained models, and you can use intuitive controls that help you and your partners tune the model’s predictive results.

AWS Clean Rooms ML was built and tested across a wide variety of datasets such as ecommerce and streaming video, and it can help customers improve accuracy on lookalike modeling by up to 36%, when compared with representative industry baselines.

AWS Clean Rooms ML is available as a capability of AWS Clean Rooms in these AWS Regions. To learn more, visit AWS Clean Rooms ML.