Architecture Overview - Predictive Segmentation Using Amazon Pinpoint and Amazon SageMaker

Architecture Overview

Deploying this solution builds the following environment in the AWS Cloud.


        Predictive Segmentation Using Amazon Pinpoint and Amazon SageMaker  solution - architectural overview

Figure 1: Predictive Segmentation Using Amazon Pinpoint and Amazon SageMaker architecture on AWS

The AWS CloudFormation template 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 Amazon Kinesis Data Streams and Amazon Kinesis Data Firehose. Amazon SageMaker performs batch transform requests to predict customer churn based on a trained machine learning (ML) model.

By default, this solution is configured to process data from the example dataset. To use your own dataset, you must modify the solution. For more information, see the appendix.