Solution components - Predictive Segmentation Using Amazon Pinpoint and Amazon SageMaker

Solution components

Amazon SageMaker

This solution uses an Amazon SageMaker notebook instance, which is a fully managed machine learning (ML) Amazon Elastic Compute Cloud (Amazon EC2) compute instance that runs the solution’s Jupyter notebook. The notebook is used to train and deploy the solution’s ML model. For more information on notebook instances, refer to Use SageMaker Notebook Instances in the Amazon SageMaker Developer Guide.


By default, the solution uses an ml.m4.xlarge instance to train the model, and an ml.m5.large instance to run batch transform requests. After the model is trained, you can terminate the model-training instance to reduce costs.


This solution contains a simple, example dataset that is used to train the solution’s ML model. The dataset includes example customer data, engagement data, and endpoint export data. The dataset is designed to train and deploy a simplistic churn model to use to demonstrate the solution’s functionality.

You can deploy and test this solution with little or no ML experience. However, to use this solution in your production environment, we recommend consulting with a data scientist to analyze and develop an ML model tailored specifically to your real customer data. For more information, refer to Customization.