Personalize your customer experiences

Grow engagement, conversion, and revenue with machine learning

As the ability to deliver more sophisticated digital experiences has evolved over time, so has the expectation and demand from customers to receive a more personalized experience from the brands they engage with across retail, media and entertainment, travel and hospitality and more. Consumers today expect real-time, curated experiences across digital channels as they consider, purchase, and use products and services.

Machine learning (ML) can help organizations deliver highly personalized experiences, resulting in improvements in customer engagement, conversion, revenue, and margin and create differentiation in a digital world.

AWS offers machine learning solutions that deliver higher-quality personalized experiences for your customers across digital channels, all tailored to your business needs.

Personalize Customer Recommendations with Machine Learning (2:41)


Cropped shot of a businessman using a digital tablet at night in an office

Deliver better personalized experiences

Solve common problems like “popularity bias” (merely showing a customer the most popular products or content) and “cold start” (where no user, item, or content history exists), which dilutes the customer experience and ability to discover new items or content in an organization’s catalog.

Woman in cafe shopping online with laptop

Increase customer engagement

Increase engagement and conversion by providing dynamic customer experiences and the optimal product or content recommendations using a blend of real-time user activity data and user profile information.

Side view of a man making a video chat at a boat

Personalize every touchpoint

Easily integrate personalization into your existing websites, apps, SMS, and email marketing systems to provide a unique customer experience across all channels and devices.

Customer stories


ResMed provides continuous positive airway pressure devices and masks for people with sleep apnea, chronic obstructive pulmonary disease, and other sleep disorders. This cloud-connected equipment collects data on patients’ sleep patterns and shares it with patients through ResMed’s myAir application. ResMed used Amazon SageMaker to rapidly build the AI/ML IHS solution that supports personalizing sleep therapy for over 18.5 million patients worldwide. 

“Prior to adopting SageMaker, all myAir users would receive the same messages from the app at the same time, regardless of their condition. We took advantage of SageMaker features to train model pipelines and to choose deployment types, including near-real time and batch inferences to deliver tailored content which helped facilitate more personalized therapy.” 

Badri Raghavan, Vice President for AI and ML - ResMed

Read the case study to learn more »

"We’re focused on how we can use data to personalize and enhance the online fan experience for our clients through the Pulselive Platform. With Amazon Personalize, we’re now providing sports fans personalized recommendations enabled by machine learning. We don’t consider ourselves machine learning experts, but found Personalize to be straight forward and the integration was complete in a few days. For one of our clients, a premier European football club with millions of fans globally, we immediately increased video consumption by 20% across their website and mobile app. Their fans are clearly embracing the new recommendations. Leveraging Amazon Personalize, we will be able to further push the limits in building data driven 1-to-1 personalized experiences for sports fans everywhere."

Wyndham Richardson, Managing Director & Co-Founder - Pulselive


Cencosud is a multinational retail company, the largest retail company in Chile, and the third largest listed retail company in Latin America. 

"Cencosud chose Amazon Personalize to optimize their online shopping experience for customers by recommending products that would boost user engagement. With Amazon Personalize, Cencosud was able to quickly develop a machine learning-based personalization solution capable of scaling across multiple types business lines leading to a 600% increase in click-through rates and a nearly 26% increase in average order value compared with their prior non-ML driven approach. The scalability and what could be achieved by using the service, as well as the option to test without having to develop large and expensive projects, led us to choose Amazon Personalize.”

Javiera Valenzuela Rivera, CRO Corporate Lead - Cencosud

Cencosud uses Amazon Personalize to Enhance the Digital Shopping Experience
Watch video testimonial »

Global software company Autodesk wanted to help architecture, engineering, and construction professionals work faster and more proficiently as they used its Autodesk AutoCAD software for computer-aided design. Autodesk has been able to increase user efficiency by providing proactive recommendations for commands and shortcuts using Amazon SageMaker. 

“We increased the number of insights by a factor of 10 by using machine learning on AWS.”

Ashish Arora, Engineering Manager - Autodesk 

Read the case study to learn more »

"Zalando's values revolve around customer focus, speed, entrepreneurship, and empowerment. We decided to standardize our machine learning workloads on AWS to improve customer experiences, give our team the tools and processes to be more productive, and push the needle in our business. Using Amazon SageMaker, Zalando can steer campaigns better, generate personalized outfits, and deliver better experiences for our customers. With this AWS-powered solution, our engineers' and data scientists’ productivity has increased by 20%."

Rodrigue Schäfer, Director Digital Foundation - Zalando

"At Zappos, we are measurably improving the ecommerce customer experience using analytics and machine learning solutions that allow us to personalize sizing and search results for individual users while preserving a highly fluid and responsive user experience. With Amazon SageMaker, we can predict customer shoe sizes. AWS is our enterprise standard for ML/AI because AWS services allow engineers to focus on improving performance and results rather than DevOps overhead."

Ameen Kazerouni, Head of Machine Learning Research and Platforms - Zappos

Use cases

Elevate the user experience

Personalize every touchpoint by integrating highly relevant, contextualized recommendations into your existing website, application,  and more.

Gain invaluable insights and a fast return on investment

Innovate faster with machine learning to quickly create meaningful user engagement while reducing the time it takes to integrate personalization into your customer experience.  

Optimize recommendations for business goals

Re-rank item recommendations to drive tangible business objectives such as revenue, upsell and cross-sell opportunities, new items, and time spend on a site. 

Help customers discover items faster

Enable users to quickly find new products, deals, articles, content, and promotions. 

Personalize search results

Add individualized recommendations based on curated search results and user preferences. 

Enhance marketing communications

Personalize push notifications and marketing emails to increase traffic conversion. You can also personalize ad placements. 

Increase average cart size

Surface relevant or trending items in real-time that are likely to increase the overall order value during shopping, browsing, or at checkout. 

Target users more accurately

Improve engagement by creating intelligent user segmentation based on a user’s affinity toward specific items or item attributes. 

Maximize the value of your data

Unlock valuable information trapped in item descriptions, reviews, or other unstructured text to increase recommendation accuracy. 

Discover Purpose-Built Services, AWS Solutions, Partner Solutions, and Guidance to rapidly address your business and technical use cases.

Maintaining Personalized Experiences with Machine Learning

Develop and deploy personalization workloads through end-to-end automation and scheduling of updates for resources within the Amazon Personalize service.

Predictive User Engagement

This Guidance provides 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.

Guidance for Predictive Scores for Member Retention on AWS

This Guidance demonstrates how nonprofits associations and membership organizations can proactively understand which members are likely to allow their membership to lapse, using AWS Data Lake and artificial intelligence/machine learning (AI/ML) services.

Guidance for Predictive Segmentation using Third-Party Data with AWS Clean Rooms

This Guidance demonstrates how AWS services can help you automate the collection of customer first-party and third-party data, enabling collaboration without sharing raw data, and generate predictive segments using machine learning. 

Guidance for Near Real-Time Personalized Recommendations on AWS

This Guidance helps businesses build a real-time recommendation pipeline using Amazon Personalize. The pipeline creates personalized recommendations based on a user’s profile and behavior to improve the customer experience. 

Ready to get started?

Contact sales
Contact us

Contact us for more information on machine learning solutions for personalization

Contact us 
Find a partner
Find a Partner

Contact the AWS Partner Network, to work with our global technology and consulting partners

Get started 
Get started with executing initiatives
Do it yourself

Use Amazon Personalize to accelerate the deployment of your personalization workload

Learn more 


Offer your customers real-time personalized recommendations using machine learning

Watch the video »

Amazon Personalize can now create up to 50% better recommendations for fast changing catalogs of new products and fresh content

Read the blog »

How dely uses Amazon SageMaker to provide personalized recipe recommendations

Read the blog »