Skip to main content

AWS Solutions Library

Guidance for Predictive Segmentation using Third-Party Data with AWS Clean Rooms

Overview

This Guidance demonstrates how AWS services can help you automate the collection of customer first-party and third-party data, enabling collaboration without sharing raw data, and generate predictive segments using machine learning. Use these predictive segments to send tailored messages through various channels including mobile push, in-app, email, SMS, or custom channels to elevate the engagement between you and your customers.

How it works

This diagram shows how first-party data is combined with third-party data to generate predictive segments in AWS Clean Rooms.

Download the architecture diagram

Well-Architected Pillars

The architecture diagram above is an example of a Solution created with Well-Architected best practices in mind. To be fully Well-Architected, you should follow as many Well-Architected best practices as possible.

With Amazon CloudWatch, you can collect and track all operational metrics, log files, and set alarms for failure. This service allows you to maintain visibility into the details of operations, such as queries run on AWS Clean Rooms.

Read the Operational Excellence whitepaper

All of the interactions between the services in this Guidance use AWS Identity and Access Management (IAM) roles with IAM policies set to provide the least privilege necessary for the services. In addition, AWS Clean Rooms enables the use of advanced cryptographic computing tools to keep data encrypted, even during query processing, to comply with the stringent data-handling policies of AWS. 

By using Amazon S3 for storage, you can encrypt all the data at rest by default. Amazon S3 provides the choice of having AWS or the customer manage the encryption keys. This helps you to adapt to your different security criteria. By using Amazon S3 bucket policies, you can define fine-grained access control. And by enabling server-side encryption on Kinesis Data Firehose, you can encrypt all sensitive data while transferring to services downstream. 

Read the Security whitepaper

Because this Guidance uses managed services, all of the stored data through the various services are highly available and not dependent on the rare, but possible, failure of an Availability Zone. Managed services help you avoid failures due to increased data volumes because of the underlying scalability of each service, such as Amazon S3 and Kinesis Data Firehose. Amazon S3 is a reliable and durable way to store your data, and Kinesis Data Firehose ensures easy, reliable data delivery to the destination for analysis in the downstream process. And we recommend using AWS Backup to back up all data stored in Amazon S3 buckets.

Read the Reliability whitepaper

This Guidance uses a serverless architecture that allows for automatic scaling of the required resources through managed services. By using Amazon Pinpoint , you can manage large volumes of customers and their interactions. And with AWS Clean Rooms, you can quickly create numerous multi-party collaborations without the need to deploy any underlying infrastructure.

Read the Performance Efficiency whitepaper

When you use managed services through a serverless architecture, you can scale your applications to accommodate demand, paying for only what you use. Amazon S3 Intelligent-Tiering automates storage cost savings by moving data when access patterns change, allowing you to optimize your performance while containing costs.

Read the Cost Optimization whitepaper

Through the extensive use of managed services coupled with a serverless architecture, this Guidance helps you continually scale to match your workload volume while ensuring that only the minimum resources are used. We also recommend managing your objects so that they are stored effectively throughout their lifecycle by configuring Amazon S3 Lifecycle.

Read the Sustainability whitepaper

Disclaimer

The sample code; software libraries; command line tools; proofs of concept; templates; or other related technology (including any of the foregoing that are provided by our personnel) is provided to you as AWS Content under the AWS Customer Agreement, or the relevant written agreement between you and AWS (whichever applies). You should not use this AWS Content in your production accounts, or on production or other critical data. You are responsible for testing, securing, and optimizing the AWS Content, such as sample code, as appropriate for production grade use based on your specific quality control practices and standards. Deploying AWS Content may incur AWS charges for creating or using AWS chargeable resources, such as running Amazon EC2 instances or using Amazon S3 storage.

Did you find what you were looking for today?

Let us know so we can improve the quality of the content on our pages