AWS First Steps
LanguageEnglish

AWS Clean Rooms ML

A privacy-preserving ML collaboration feature that enables multiple organizations to jointly train and run inference on machine learning models without sharing raw data

About 4 min read

Overview

AWS Clean Rooms ML is an extension of AWS Clean Rooms that enables multiple organizations to jointly execute machine learning model training and inference without directly sharing raw data. It allows data collaboration partners such as advertisers and publishers, or retailers and manufacturers, to build lookalike audiences and conversion prediction models while preserving privacy. It provides privacy-enhancing controls that help each participant safeguard their data and model IP, reducing the risk of individual record identification. It makes cross-organization ML utilization, previously difficult due to legal and technical barriers, easily accessible as a managed service.

Lookalike Audience Generation with Lookalike Modeling

The representative use case for Clean Rooms ML is Lookalike Modeling (lookalike audience generation). It matches an advertiser's high-value customer list (seed data) against a publisher's user attribute data to generate new target audiences with characteristics similar to the seed customers. This processing executes within the Clean Rooms collaboration environment; the advertiser cannot see the publisher's individual user data, and the publisher cannot see the details of the advertiser's customer list. The generated lookalike audience is output as segments with similarity scores, which can be linked to ad delivery platforms to improve targeting precision. Model training is automated, allowing execution from the console without ML expertise.

Technical Mechanisms for Privacy Protection

Clean Rooms ML's privacy protection consists of multiple technology layers. First, collaboration analysis rules restrict the scope and aggregation level of data each participant can access. Differential privacy in AWS Clean Rooms adds calibrated noise to analytical query results, making it difficult to re-identify individual records (check the official AWS documentation for how it applies to ML processing). The privacy budget concept manages the accumulation of privacy risk through cumulative queries, automatically blocking queries that exceed the budget. For ML processing, privacy-enhancing controls help data owners safeguard their data and their model IP. Audit logs are recorded in CloudTrail, enabling tracking of who executed what analysis and when.

Collaboration Design and Practical Considerations

Utilizing Clean Rooms ML requires first establishing collaboration agreements between partners. Data usage purposes, analysis rules (minimum aggregation units, permissible output metrics), and privacy budget allocation must be determined in advance and reflected in Clean Rooms collaboration settings. In practice, legal department review of data usage agreements and technical team design of analysis rules can proceed in parallel. Pricing is usage-based: for Lookalike Modeling you pay for the model trainings you request and the segments created, and for custom models for the records processed and the compute you use (as of September 2026; check the official AWS pricing page for current units and rates). For Lookalike Modeling, the number of trainings and the size of the generated segments affect cost, so improving seed quality and sizing segments to what you need helps manage spending. The model is not retrained automatically; the official AWS documentation recommends weekly retraining (as of September 2026), so set the frequency based on audience change velocity, balancing freshness against cost.

References (Official AWS Resources)

The primary sources for this page are the official AWS website and documentation. Check the official pages below for the latest specifications and pricing.

If this page and the official documentation disagree, treat the official documentation as authoritative.

Share

Related Terms

AWS Clean RoomsAWS Lake FormationAmazon SageMakerAWS Glue

Related Services

AWS Clean RoomsAWS Lake FormationAmazon SageMakerAmazon S3

Related Articles

Privacy-Preserving Data Collaboration with AWS Clean RoomsRun joint analysis across multiple companies without sharing or copying data. Learn about aggregation rules for preventing individual identification and Cryptographic Computing for encrypted analysis.Privacy-Preserving ML with AWS Clean Rooms ML - Build Models Without Sharing DataLearn how to build lookalike models with Clean Rooms ML, apply differential privacy, and leverage the results for ad targeting.Building a Data Lake with Amazon S3 and Lake Formation - Design Patterns and GovernanceThis article introduces data lake design patterns that use S3 as the storage foundation and achieve fine-grained access control with Lake Formation. It also explains ETL pipelines and cost optimization.Privacy-Preserving Data Analytics - Collaborating on Data Securely with AWS Clean RoomsThis article explains privacy-preserving data analytics using AWS Clean Rooms. It introduces data collaboration among multiple organizations, access control with analysis rules, and making use of differential privacy.No-Code ML with Amazon SageMaker Canvas - Building Prediction Models with a Visual InterfaceA visual tool for building ML models without writing code. Simply upload a CSV and select a prediction target to build a model, with bidirectional sharing with Studio.

Similar Terms and Articles

Privacy-Preserving ML with AWS Clean Rooms ML - Build Models Without Sharing DataLearn how to build lookalike models with Clean Rooms ML, apply differential privacy, and leverage the results for ad targeting.AWS Clean Rooms MLA service for building ML models within Clean Rooms while preserving privacyPrivacy-Preserving Data Analytics - Collaborating on Data Securely with AWS Clean RoomsThis article explains privacy-preserving data analytics using AWS Clean Rooms. It introduces data collaboration among multiple organizations, access control with analysis rules, and making use of differential privacy.AWS Clean RoomsA privacy-preserving data collaboration service that enables multiple organizations to jointly analyze data without sharing itPrivacy-Preserving Data Collaboration with AWS Clean RoomsRun joint analysis across multiple companies without sharing or copying data. Learn about aggregation rules for preventing individual identification and Cryptographic Computing for encrypted analysis.