Table of Contents
Artificial intelligence (AI) is revolutionizing the way enterprises conduct business. Companies are leveraging AI to enhance data-driven decision-making, improve omnichannel experiences, and drive the development of next-generation products. One area where AI is being extensively used is in marketing efforts, specifically through emails, push notifications, and other outbound communication channels. According to Gartner, by 2025, 30% of outbound marketing messages from large organizations will be synthetically generated using generative AI.
However, while generative AI is a powerful tool, it is not sufficient on its own to deliver engaging customer communication. Research shows that personalized communication is the most impactful, as customers expect companies to deliver personalized interactions. McKinsey reports that 71% of consumers expect personalized interactions. To achieve this level of personalization, companies can combine generative AI with Amazon Personalize, a machine learning (ML) technology used by Amazon.com for real-time personalized recommendations.
Using Amazon Personalize for Personalized Marketing
Amazon Personalize allows developers to build applications powered by ML technology to improve user engagement through personalized product and content recommendations. It offers pre-built algorithms, known as recipes, that support specific use cases such as product recommendations, personalized ranking, and user segmentation. With Amazon Personalize, developers can integrate personalized recommendations into existing websites, applications, email marketing systems, and more without requiring ML expertise.
Elevating Marketing Campaigns with Amazon Personalize and Generative AI
By combining Amazon Personalize with generative AI using Amazon Bedrock, marketers can tailor their marketing campaigns to individual consumer preferences. Let’s explore two use cases that illustrate how Amazon Personalize and Amazon Bedrock work together to achieve this.
Use Case 1: Targeted One-to-One Personalized Emails
In this use case, Amazon Personalize and Amazon Bedrock are used to generate personalized recommendations and create targeted one-to-one personalized emails.
Architecture and Workflow
Here is the architecture and workflow for delivering targeted personalized emails powered by generative AI:
-
Import the dataset of users’ interactions into Amazon Personalize for training. Amazon Personalize automatically trains a model using the Top Picks for You recipe, which provides recommendations aligned with users’ preferences.
-
Use the Amazon Personalize API to identify recommended items for users.
python
get_recommendations_response = personalize_runtime.get_recommendations(
recommenderArn=workshop_recommender_top_picks_arn,
userId=str(user_id),
numResults=number_of_movies_to_recommend
)
-
Ingest the provided output of recommendations into Amazon Bedrock using a prompt that includes user preferences, demographics, and Amazon Personalize recommended items.
-
Invoke one of the foundation models (FM) provided in Amazon Bedrock, such as Claude 2, with the prompt to generate a personalized email.
python
personalized_email_response = bedrock_client.invoke_model(
body=prompt,
modelId=identifier_of_the_model
)
- Amazon Bedrock returns a personalized email for the user.
Example Personalized Email
Subject: Fall in love with this recommended selection for movie night!
Dear [user name],
Desiring the cozy feel of fall? No problem! Check our top three recommendations for movies that will have you cozy on the couch with your loved ones:
-
The Little Mermaid: This classic Disney movie is all about a mermaid princess named Ariel, who dreams of the human world. Because of her fascination, she makes a deal with the sea witch Ursula and learns a major lesson.
-
Encanto: 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.
-
Spider-Man: Into the Spider-Verse: This animated superhero movie is a must-see action movie. Spider-man, a Brooklyn teen named Miles Morales, teams up with other spider-powered people to save the multiverse. With lovable characters, catchy tunes, and moving 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: Elevating One-to-Many Marketing Campaigns
In this use case, Amazon Personalize and Amazon Bedrock are used to elevate one-to-many marketing campaigns by creating variations of email content with greater relevance and engagement.
Architecture and Workflow
Here is the architecture and workflow for elevating marketing campaigns powered by generative AI:
-
Import the dataset of users’ interactions into Amazon Personalize for training. Amazon Personalize trains the model using the user segmentation recipe, which automatically identifies individual users with a propensity for specific items as the target audience.
-
Use the Amazon Personalize API to create a batch segment job to identify the target audience and retrieve metadata for an item.
python
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
}
}
)
-
Amazon Personalize delivers a list of recommended users to target for each item.
-
Invoke the user segment into Amazon Bedrock using one of the foundation models (FM) along with a prompt.
python
personalized_email_response = bedrock_client.invoke_model(
body=prompt,
modelId=identifier_of_the_model
)
- Amazon Bedrock returns a personalized email based on the chosen items for each user.
Example Personalized Email
Subject: <>, your ticket to the Hall of Fame awaits
Hey <>,
The wait is over. Check out the new Ultra Fame II! It’s the most innovative and comfortable Ultra Fame shoe yet. Its new design will have you turning heads with every step. Plus, you’ll get a mix of comfort, support, and style that’s just enough to get you into the Hall of Fame.
Don’t wait until it’s too late. Use the code FAME10 to save 10% on your next pair.
Conclusion
By integrating Amazon Personalize and Amazon Bedrock, marketers can deliver personalized promotional content to the right audience. Generative AI powered by foundation models is transforming how businesses create hyper-personalized experiences for consumers. AWS AI services like Amazon Personalize and Amazon Bedrock provide the tools to recommend and deliver products, content, and compelling marketing messages personalized to users’ preferences. To learn more about working with generative AI on AWS, visit the https://aimarketingmonster.com website.
About the Authors
Ba’Carri Johnson is a Sr. Technical Product Manager working with AWS AI/ML on the Amazon Personalize team. With a background in computer science and strategy, she is passionate about product innovation. In her spare time, she enjoys traveling and exploring the great outdoors.
Ragini Prasad is a Software Development Manager with the Amazon Personalize team focused on building AI-powered recommender systems at scale. In her spare time, she enjoys art and travel.
Jingwen Hu is a Sr. Technical Product Manager working with AWS AI/ML on the Amazon Personalize team. In her spare time, she enjoys traveling and exploring local food.
Anna Grüebler is a Specialist Solutions Architect at AWS focusing on artificial intelligence. She has more than 10 years of experience helping customers develop and deploy machine learning applications. Her passion is taking new technologies and putting them in the hands of everyone and solving difficult problems by taking advantage of using AI in the cloud.
Tim Wu Kunpeng is a Sr. AI Specialist Solutions Architect with extensive experience in end-to-end personalization solutions. He is a recognized industry expert in e-commerce and media and entertainment, with expertise in generative AI, data engineering, deep learning, recommendation systems, responsible AI, and public speaking.
