Overview - Predictive User Engagement


Given the ever-increasing number of brands competing for a finite amount of customer attention, maximizing customer engagement is vital. In today’s digital marketplace, it is critical to keep your users coming back to your app.

One method that can help improve customer engagement is to deliver personalized messaging to your users. Personalized messaging can help build trust in your brand and increase conversion rates. Amazon Pinpoint helps you engage with your customers by sending personalized email, SMS and voice messages, and push notifications. With Amazon Pinpoint, you can place your customers in groups based on demographics, behaviors, or other key performance indicators that are important for your business, and send highly personalized, timely, and relevant messages to those groups.

Machine learning (ML) can also help you improve your customer engagement by analyzing your customer activity, identifying patterns, and making recommendations to help you convert users. However, it can be a challenge to integrate ML models with messaging tools for companies without deep, in-house ML expertise.

To help you more easily leverage the personalized messaging engine of Amazon Pinpoint with machine learning without ML expertise, AWS offers the Predictive User Engagement solution. This solution combines Amazon Pinpoint and Amazon Personalize, an ML service that analyzes user activity against predefined ML models and makes recommendations.

With Predictive User Engagement, you can build a simple architecture that automates the process of making predictive recommendations based on user activity in Amazon Personalize, and updating Amazon Pinpoint endpoints with those recommendations.

This solution is designed to provide a simple architecture to demonstrate how to use ML to make product recommendations and automatically update your endpoints and segments. You can build upon this architecture for a variety of use cases.


You are responsible for the cost of the AWS services used while running this solution. The cost for running this solution depends on the number of SMS messages you send, the number of endpoints you contact, the amount of data this solution ingests, how many compute hours it takes to train your ML model, the number of AWS Lambda requests, and how much compute time the Lambda function uses. Prices are subject to change. For full details, see the pricing webpages for Amazon Pinpoint, Amazon Personalize, and AWS Lambda.