Overview - Amazon Personalize Optimizer Using Amazon Pinpoint Events


Today's consumer expects a high level of personalization in order to continue engaging with a company. To address this challenge, customers use curated messaging, rather than a generalized marketing campaign, to lower churn rates, increase consumer interaction, and drive higher conversion rates. Many customers are turning to machine learning to deliver personalized product recommendations or promotions at scale. In order to maintain an effective and relevant model, you need high volumes of recent behavioral data. Without an automated data pipeline, you have to perform inefficient manual retraining or risk using an outdated model. You depend on an engineering team to build and maintain automated pipelines, delaying the time to deploy their models.

To help you leverage your existing Amazon Personalize campaigns and Amazon Pinpoint projects to build a data pipeline easily, AWS offers the Amazon Personalize Optimizer Using Amazon Pinpoint Events solution. This solution empowers you to train and publish models quickly without support from an engineer. You can define the frequency and the type of data used to retrain your models. Using an automated retraining loop frees you to build new models and keep them relevant for your marketers.

This guide provides infrastructure and configuration information for planning and deploying the Amazon Personalize Optimizer Using Amazon Pinpoint Events solution in the AWS Cloud. This automated reference implementation deploys a cost-effective, end-to-end solution for creating a scheduled daily batch to gather select consumer data and then use the data to retrain a personalization model. The personalization model can then be used with Amazon Pinpoint to personalize messaging content.


You are responsible for the cost of the AWS services used while running this reference deployment. As of the date of publication, the cost for running this solution with default settings in the US East (N. Virginia) Region is approximately $140 a month. The cost estimate includes the use of Amazon Pinpoint and AWS Lambda to retrain your Amazon Personalize model using AWS Glue, AWS Lambda, Amazon Athena, Amazon CloudWatch, and Amazon Kinesis. This estimate assumes 100,000 customer endpoints stored in Amazon Pinpoint with up to 1 GB of additional customer data in Amazon Simple Storage Service (Amazon S3).


This solution requires that you have already deployed an Amazon Personalize campaign and Amazon Pinpoint project in your environment. The cost estimate does not include the costs of running your existing Amazon Personalize, Amazon Pinpoint, and AWS Lambda functions already deployed in your environment.

Prices are subject to change. For full details, see the pricing webpage for each AWS service you will be using in this solution.