Predictive Segmentation Using Amazon Pinpoint and Amazon SageMaker combines Amazon Pinpoint with Amazon SageMaker to help automate the process of collecting customer data and creating Amazon Pinpoint segments identified by Machine Learning (ML) for tailored audience messaging. These segments can include users predicted to churn, users predicted to make a purchase, and other predicted user behaviors relevant to your business needs.
This Guidance includes a sample dataset that you can use as a reference to develop your own custom ML models using your own data.
Deploying Digital User Engagement Events Database is a prerequisite to deploying this Guidance.
The diagram below presents the architecture you can build using the example code on GitHub.
Predictive Segmentation Using Amazon Pinpoint and Amazon SageMaker architecture
The code deploys a daily batch process orchestrated by AWS Step Functions. The process begins when an Amazon CloudWatch time-based event triggers a series of AWS Lambda functions that use an Amazon Athena query to query customer data stored in Amazon Simple Storage Service (Amazon S3). The data is crawled daily by AWS Glue.
The customer data includes endpoints exported from Amazon Pinpoint and end-user engagement data streamed from Amazon Pinpoint using the Digital User Engagement Events Database solution. Amazon Sagemaker performs batch transform requests to predict customer churn based on a trained machine learning (ML) model.
By default, Predictive Segmentation Using Amazon Pinpoint and Amazon SageMaker is configured to process data from the sample dataset. To use your own dataset, you must customize the Guidance.
Browse our library of AWS Solutions to get answers to common architectural problems.
Find AWS Partners to help you get started.
Find prescriptive architectural diagrams, sample code, and technical content for common use cases.