This document summarizes a webinar about using Amazon Personalize for recommendations on WooCommerce stores. It introduces Amazon Personalize and how it works, demonstrating how to set it up through the AWS for WordPress plugin. It provides examples of how businesses have benefited from personalization. It also discusses considerations for getting started and pricing. Finally, it explores ways to extend personalization through custom plugins, such as integrating recommendations into a chat experience.
Use Amazon.com personalization on your WooCommerce store.
1. #wpewebinar
James Jory & Igor Krtolica, Amazon Web Services
Anthony Burchell, WP Engine
Use Amazon.com personalization on
your WooCommerce store.
New Amazon for WordPress plugin features,
co-authored with WP Engine.
2. #wpewebinar
What You’ll Learn
● Why personalization is important
● What AWS Personalize for WooCommerce is
● How AWS Personalize works - demo and next steps
3. #wpewebinar
Ask questions as we go.
We’ll answer as many questions as we can after
the presentation
Slides and recording will be
made available shortly after
the webinar
Use the “Questions” pane
throughout the webinar
4. #wpewebinar
Igor Krtolica
Solutions Architect, Applied AI
Amazon Web Services
James Jory
● Dabbled in winemaking and
growing grapes
● Simulation racer in spare
time
● Wannabe BBQ pitmaster
● Worked with Personalize
during beta
● Loves good coffee
● Misses in-person
presentations
Partner Solutions Architect
Amazon Web Services
Anthony Burchell
● WordPress core
committer
● VR/AR Enthusiast
● Makes music on a
Gameboy
WordPress Developer
WP Engine Labs
18. #wpewebinar
Amazon Personalize Components
User / Item
Interactions
Catalog
Data
Interactions
Dataset
Solution
Version(s)
Recipe
Event
Tracker
Campaign
Personalized
Recommendation
s
Dataset
Group
Solution
User
Data
Users Dataset
Items Dataset
Filters
User
Behavior
19. #wpewebinar
WooCommerce and Personalize Architecture
AWS Cloud
AWS for Wordpress
Plugin
Amazon Personalize
Datasets
Train
Models
Recommendation
Function
User Events
Event Tracker
WooCommerce
User Interactions
Product
Recommendations
20. #wpewebinar
• 25 unique users
• 1,000 interactions
• 100 products
• Users must be known / logged in
Things to consider before getting started
Recommended Minimum Requirements
Deploying Amazon Personalize
21. #wpewebinar
$0.05 / Gigabyte
uploaded to Amazon
Personalize. This
includes data sent in real
time via trackers.
Data Ingestion
$0.24 / training hour for
the training hours
consumed to train a
custom model with your
data.
// First 20K TPS-hour per month
$0.20 per TPS-hour for real-time
recommendations
// Next 180K TPS-hour per month
$0.10 per TPS-hour for real-time
recommendations
// Over 200K TPS-hour per month
$0.05 per TPS-hour for real-time
recommendations
Training Time Real-Time
Recommendations
Amazon Personalize Pricing
See https://aws.amazon.com/personalize/pricing/ for
more details.
23. #wpewebinar
Don’t...if you are already using
WooCommerce, you can add
machine-learning powered
personalization using the AWS
WordPress plugin.
Setting up recommended
products the hard way?
Install the AWS WordPress Plugin
Enter your AWS account ID (this is required)
Enable the Amazon Personalize integration
Train an Amazon Personalize solution
Deploy recommendations to your WooCommerce site
Set up AWS services directly from the Admin console
Personalization
AWS Wordpress Plugin Setup
25. #wpewebinar
Setup
• “New Products in Recommendations”
▪ for when new products are
added after training is
complete.
• Manual cycle for training is
recommended for lower traffic
shops.
26. #wpewebinar
New Products in
Recommendations
Start Training
createPersonalizeFullAccessPolicy
createPersonalizeS3BucketAccessPolicy
createPersonalizeS3BucketAccessPolicyBatch
createS3BucketAccessPolicy
createS3BucketAccessPolicyBatch
createRole
createDatasetGroup
createInteractionsSchema
createItemsSchema
createInteractionsDataset
createItemsDataset
uploadCustomersCSV
uploadProductsCSV
uploadInteractionsCSV
createDatasetImportJob
getDatasetImportJobStatus
createSolution
getSolutionStatus
createSolutionVersion
getSolutionVersionStatus
createCampaign
28. #wpewebinar
When training completes, recommendations will start
AWS Cloud
AWS for Wordpress
Plugin
Amazon Personalize
Datasets
Train
Models
Recommendation
Function
User Events
Event Tracker
WooCommerce
User Interactions
Product
Recommendations
30. #wpewebinar
Recommendations Results
• A simple way to track the success and details of
your campaigns.
• On submit of a purchase the total is added to the
campaign total.
• More to come as we refine tracking results!
33. #wpewebinar
Use Case:
Use Case: ML Assisted Shopping Experience
CRM
Chat/Support
Product
Recommendations
From userID
Or hide ID!
AWS Cloud
AWS for
Wordpress
Plugin
Amazon
Personalize
Datasets
Train
Models
Recommendation
Function
User Events
Event Tracker
WooCommerce
User Interactions
Product
Recommendations
34. #wpewebinar
ML assisted customer experience
• Easy to pass data from your WooCommerce shop to
other apps.
• In this example, a chat app is sending personalized
data about the shopper to the agent while hiding
the identity of the shopper.
• Personalization can be a tool to closer engage with
your customers. ML assisting Humans!
Chat Agent Dashboard