AWS Clean Rooms ML

Apply ML with your partners without sharing underlying data

AWS Clean Rooms ML helps you and your partners apply privacy-enhancing machine learning (ML) to generate predictive insights without having to share raw data with each other. The capability's first model is specialized to help 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 you and your partners' underlying data. Healthcare modeling will be available in the coming months.

Introducing AWS Clean Rooms ML

Benefits of AWS Clean Rooms ML

AWS Clean Rooms ML models are natively built within the service, helping you protect your datasets and customers' information. The models are tested across various datasets including e-commence, news, and streaming channels, removing the need to share your data with partners to train a model.
AWS Clean Rooms ML trains a custom, private ML model for you and your partners. With AWS Clean Rooms ML, your data is only used to train your model. Data is not shared with either party, and you can remove your data or delete a custom model whenever you want.
AWS Clean Rooms ML helps companies collaborate to generate predictive insights using ML in a few steps, instead of spending months building, training, tuning, and deploying their own models.
AWS Clean Rooms ML provides intuitive controls that help you and your partners tune the results of the applied ML model to garner predictive insights.

Use cases

Airlines can take data about loyal customers, collaborate with online booking services, and offer promotions to users with similar characteristics.

Auto lenders and insurers can identify prospective auto insurance customers who share characteristics with a set of existing lease owners.

Brands and publishers can model lookalike segments of in-market customers and deliver highly relevant advertising experiences.

Research institutions and hospital networks can find candidates who are similar to existing clinical trial participants to accelerate clinical studies (coming soon).

Customers and partners

Amazon Marketing Cloud (AMC) is a secure, privacy-safe clean room application from Amazon Ads that supports thousands of marketers with custom analytics and cross-channel analysis. Builders can use AMC APIs to create their own offerings, while analysts can interact with a user interface available through the Amazon Ad console.

“AMC Audiences now offers new custom lookalike audiences, powered by AWS Clean Rooms ML, which can be activated on campaigns in the Amazon DSP and help advertisers unlock incremental audience reach in line with their goals. Since its launch in October 2023, this capability enabled a leading CPG brand to reach new prospects and increase campaign performance.”

Paula Despins, Vice President of Ads Measurement, Amazon Ads

Slalom is a global business and technology consulting company.

"We are always looking to partner with our publisher clients to update their technology stack so they can more easily unlock the full potential of their high-quality ad inventory. AWS Clean Rooms ML's highly accurate ML modeling is very compelling as publishers look for ways to improve advertising effectiveness. AWS Clean Rooms ML provides an easy-to-use interface that publishers and brands can use to identify the right users for an ad campaign, while protecting sensitive data of both parties."

Mukesh Kumar, General Manager of the Global Technology Team, Slalom

Experian gathers, analyzes, and processes credit data at massive scale to help businesses make smarter decisions, individuals gain access to financial services, and lenders minimize risk.

"As marketers and publishers seek to maximize the value of their first-party data across a growing number of consumer touch points, our customers want solutions that enable them to effectively and securely interact with their partners. AWS Clean Rooms ML enables our marketer customers to use their first-party data in combination with our unique consumer data, such as vehicle purchase information, to find prospective users on publisher sites that resemble the marketer's current best customers without revealing sensitive data to partners."

Chris Feo, SVP of Sales, Experian

Twilio Segment is a leading customer data platform (CDP) that accelerates client business growth through advertising effectiveness.

“Never has it been more important to focus on quality, real-time first-party data as businesses launch more AI-driven campaigns. Our recent report shows that 85% of businesses are prioritizing capturing and leveraging first-party data better in the coming year. Leveraging AWS Clean Rooms ML modeling helps protect our customers’ valuable first-party data while empowering them to reach high-value prospecting audiences through collaboration with their preferred media publishers.”

Kathryn Murphy, SVP of Product, Twilio Segment

Affinity Solutions, a leader in consumer purchase insights, uses data from over 140 million cards to provide an unparalleled view of US consumer spending, transforming data into actionable insights that drive market share and revenue growth.

“Affinity Solutions is at the forefront of balancing privacy with providing comprehensive consumer insights. With AWS Clean Rooms ML, our marketer clients will be able to leverage our deterministic dataset as seed data for creating advanced lookalike models in combination with their own data. This empowers companies to identify potential purchasers across platforms, while adhering to privacy standards and providing potent, actionable insights for today's privacy-conscious market.”

Atul Chadha, Chief Technology Officer, Affinity Solutions

The Weather Company provides weather data and insights to consumers, brands, and businesses across the globe.

“The Weather Company is testing AWS Clean Rooms as a practical way to enable advertisers to analyze their first-party data together with weather data and use predictive machine learning to identify engaged audiences, at scale, based on weather’s impact to people’s daily lives. AWS Clean Rooms offers a streamlined  capability that accelerates time to value, enabling lookalike segment creation in a few clicks, while helping us protect the data of the hundreds of millions of consumers who visit our digital properties each month.”

Dave Olesnevich, Head of Advertising Products, The Weather Company

StellarAlgo is a leading customer cloud platform for the sports and live audience industry, partnered with more than 110 properties across North America, including league-wide relationships with the NFL, NHL, and NBA.

“As a leader in helping the world’s leading sports and live entertainment brands understand, grow, and monetize their audiences, we are thrilled that AWS Clean Rooms continues to innovate rapidly to empower our clients to succeed. AWS Clean Rooms ML modeling helps our clients identify and engage high-value prospects, allowing them to execute more effective, resonant partnerships—all while enabling us to help protect their sensitive first-party data. We are thrilled that AWS Clean Rooms continues to innovate rapidly to empower our clients’ success.”

Greg Sargent, SVP Sports Partnerships, StellarAlgo

BRIDGE is a people-based omni-channel marketing platform that helps customers market to their true buying audience.


“At BRIDGE, we are excited to use AWS Clean Rooms ML to support our lookalike audience builder—enabling our clients to securely leverage our real people datasets to better understand their CRM files and find their next customer. AWS Clean Rooms ML supports BRIDGE’s goal to provide privacy-first collaboration tools that improve consumer intelligence and drive marketing outcomes more effectively.”