Improve your marketing solutions with Amazon Personalize and generative AI

Generative artificial intelligence is transforming the way companies do business. Organizations are using ai to improve data-driven decisions, enhance omnichannel experiences, and drive next-generation product development. Companies are using generative ai specifically to boost their marketing efforts through emails, push notifications, and other outbound communication channels. Gartner ai-for-enterprises” target=”_blank” rel=”noopener”>predict that “by 2025, 30% of outbound marketing messages from large organizations will be generated synthetically.” However, generative ai alone is not enough to deliver engaging customer communication. Research shows that the most impactful communication is personalized: showing the right message to the right user at the right time. According McKinsey, “71% of consumers expect companies to offer personalized interactions.” Customers can use Amazon Personalize and generative ai to curate concise, personalized content for marketing campaigns, increase ad engagement, and enhance conversational chatbots.

Developers can use Amazon Personalize to create applications powered by the same type of machine learning (ML) technology used by Amazon.com for personalized recommendations in real time. With Amazon Personalize, developers can improve user engagement through personalized product and content recommendations without requiring machine learning expertise. Using recipes (algorithms prepared to support specific use cases) provided by Amazon Personalize, customers can offer a wide range of personalization, including specific product or content recommendations, personalized ranking, and user segmentation. Additionally, as a fully managed ai service, Amazon Personalize accelerates customers’ digital transformations with ML, making it easy to integrate personalized recommendations into websites, apps, email marketing systems, and more.

In this post, we illustrate how you can improve your marketing campaigns using Amazon Personalize and generative ai with Amazon Bedrock. Together, Amazon Personalize and generative ai help you tailor your marketing to individual consumer preferences.

How exactly do Amazon Personalize and Amazon Bedrock work together to achieve this? Imagine that, as a marketer, you want to send personalized emails to users recommending movies they would enjoy based on their interactions on your platform. Or maybe you want to send targeted emails to a segment of users promoting a new shoe they might be interested in. The following use cases use generative ai to improve two common marketing emails.

Use Case 1: Use Generative ai to Send Personalized One-to-One Emails

With Amazon Personalize and Amazon Bedrock, you can generate personalized recommendations and create outbound messages with a personal touch tailored to each of your users.

The following diagram illustrates the architecture and workflow for delivering targeted personalized emails powered by generative ai.

First, import your user interaction dataset into Amazon Personalize for training. Amazon Personalize automatically trains a model using the Top Picks for You recipe. As a result, Amazon Personalize provides recommendations that align with users’ preferences.

You can use the following code to identify recommended items for users:

get_recommendations_response = personalize_runtime.get_recommendations(
                            recommenderArn = workshop_recommender_top_picks_arn,
                            userId = str(user_id),
                            numResults = number_of_movies_to_recommend)

For more information, see the Amazon Personalize API Reference.

Amazon Bedrock ingests the recommendation result provided via a message that includes your user preferences, demographic data, and recommended items from Amazon Personalize.

For example, a marketer who wants to create a personalized email that is charming and fun for a user might use the following message:

Create a personalized, charming and fun email to engage the user. The user has recently watched family movies. These are the recommended items: The Little Mermaid, Charming, Spider-Man: Into the Spider-Verse.

By invoking one of the basic models (FM) provided on Amazon Bedrock, such as Claude 2, with the message and sample code below, you can create a custom email for a user:

personalized_email_response = bedrock_client.invoke_model(
                            body = prompt,
                            modelId = identifier_of_the_model)

For more information, see the Amazon Bedrock API Reference.

Amazon Bedrock returns a personalized email to the user:

Subject: Fall in love with this recommended selection for a movie night!

Dear ,

Craving the cozy feeling of fall? No problem! Check out our top three movie recommendations that will make you cozy on the couch with your loved ones:

1. The Little Mermaid: This classic Disney movie is about a mermaid princess named Ariel, who dreams of the human world. Out of her fascination, she makes a deal with the sea witch Ursula and learns an important lesson.

2. Charm: This Disney movie is about the Madrigals, a Colombian family who lives in a magical house. Each member of the family has a unique gift, except for young Maribel who must help save her family.

3. Spider-Man: Into the Spider-Verse: This animated superhero film is a must-see action movie. Spider-Man, a Brooklyn teenager named Miles Morales, teams up with other people with spider powers to save the multiverse.

With lovable characters, catchy tunes, and heartwarming stories, you really can’t go wrong with any of these three. Grab the popcorn because you’re in for a treat!

Use Case 2: Use Generative ai to Improve One-to-Many Marketing Campaigns

When it comes to one-to-many email marketing, generic content can lead to low engagement (i.e. low open rates and low opt-ins). One way businesses avoid this outcome is to manually create variations of outbound messages with catchy subject lines. This can lead to inefficient use of time. By integrating Amazon Personalize and Amazon Bedrock into your workflow, you can quickly identify the segment of interested users and create email content variations with greater relevance and engagement.

The following diagram illustrates the architecture and workflow for improving marketing campaigns powered by generative ai.

To compose one-to-many emails, first import your data set of user interactions into Amazon Personalize for training. Amazon Personalize trains the model using the user segmentation recipe. With the user segmentation recipe, Amazon Personalize automatically identifies individual users who demonstrate a propensity for the items chosen as your target audience.

To identify the target audience and retrieve metadata for an item, you can use the following sample code:

create_batch_segment_response = personalize.create_batch_segment_job(
        jobName = job_name,
        solutionVersionArn = solution_version_arn,
        numResults = number_of_users_to_recommend
        jobInput =  {
            "s3DataSource": {
                "path": batch_input_path
            }
        },
        jobOutput = {
            "s3DataDestination": {
            "path": batch_output_path
            }
        }
)

For more information, see the Amazon Personalize API Reference.

Amazon Personalize provides a list of recommended users to target for each item. batch_output_path. You can then invoke the user segment on Amazon Bedrock using one of the FMs along with your message.

For this use case, you might want to market a newly released sneaker via email. An example message could include the following:

For the “sneaker heads” segment of users, create an engaging email promoting the latest “Ultra Fame II” sneaker. Provide users with discount code FAME10 to save 10%.

Similar to the first use case, you will use the following code in Amazon Bedrock:

personalized_email_response = bedrock_client.invoke_model(
                                body = prompt,
                                modelId = identifier_of_the_model)

For more information, see the Amazon Bedrock API Reference.

Amazon Bedrock returns a personalized email based on the items chosen for each user, as shown:

Affair:>, your ticket to the Hall of Fame awaits you

Hello>,

The wait is over. Check out the new Ultra Fame II! It is the most innovative and comfortable Ultra Fame shoe so far. Its new design will make you attract attention with every step. Plus, you’ll get enough of a combination of comfort, support, and style to get you into the Hall of Fame.

Don’t wait until it’s too late. Use code FAME10 to save 10% on your next pair.

To test and determine the email that generates the most engagement, you can use Amazon Bedrock to generate a variation of engaging subject lines and content in a fraction of the time it would take to produce test content manually.

Conclusion

By integrating Amazon Personalize and Amazon Bedrock, you can deliver personalized promotional content to the right audience.

FM-powered generative ai is changing the way companies create hyper-personalized experiences for consumers. AWS ai services, such as Amazon Personalize and Amazon Bedrock, can help recommend and deliver engaging products, content, and marketing messages personalized to your users. For more information about working with Generative ai on AWS, see Announcing New Tools for Building with Generative ai on AWS.

About the authors

Not Carrie Johnson is a Senior Technical Product Manager working with AWS ai/ML on the Amazon Personalize team. With a background in IT and strategy, he is passionate about product innovation. In his spare time, he enjoys traveling and exploring the outdoors.

Ragini Prasad is a software development manager on the Amazon Personalize team focused on building ai-powered recommendation systems at scale. In her free time she enjoys art and traveling.

Jingwen Hu is a Senior Technical Product Manager working with AWS ai/ML on the Amazon Personalize team. In his free time, he likes to travel and explore local food.

Anna Gruebler is an AWS-focused solutions architect focusing on artificial intelligence. He has over 10 years of experience helping clients develop and deploy machine learning applications. His passion is taking new technologies and putting them in everyone’s hands and solving difficult problems by leveraging the use of ai in the cloud.

Wu Kunpeng Team is a Senior Solutions Architect specializing in ai with extensive experience in end-to-end personalization solutions. He is a recognized industry expert in e-commerce, media and entertainment, with expertise in generative ai, data engineering, deep learning, recommendation systems, responsible ai and public speaking.