Overview
Maintaining Personalized Experiences with Machine Learning helps you build custom HAQM Personalize experiences for your product portfolio, including custom recommendation models at scale. This AWS Solution streamlines and accelerates the development and deployment of your personalization workloads through automation and scheduled updates for resources within HAQM Personalize.
Benefits
Automate the creation of all resources in HAQM Personalize upfront to save on time and costs.
Integrate workflows around HAQM Personalize into your applications.
Technical details
You can automatically deploy this architecture using the implementation guide and the accompanying AWS CloudFormation template.
Step 1
The AWS CloudFormation template deploys an HAQM Simple Storage Service (HAQM S3) bucket used to store personalization data and configuration files.
Step 2
An AWS Lambda function initiated when new or updated personalization configuration is uploaded to the personalization data bucket.
Step 3
An AWS Step Functions workflow manages all of the resources of an HAQM Personalize dataset group (including datasets, schemas, event tracker, filters, solutions, campaigns, and batch inference jobs).
Step 4
HAQM CloudWatch metrics for HAQM Personalize for each new trained solution version are added to help you evaluate the performance of a model over time.
Step 5
An HAQM Simple Notification Service (HAQM SNS) topic and subscription notifies an administrator when the maintenance workflow has completed via email.
Step 6
HAQM DynamoDB tracks the scheduled events configured for HAQM Personalize to fully or partially retrain HAQM Personalize solutions, import or reimport datasets, and perform batch inference jobs.
Step 7
A Step Functions workflow tracks the current running scheduled events, and invoke step functions to perform HAQM Personalize solution maintenance (creating new solution versions, updating campaigns), import updated datasets, and perform batch inference.
Step 8
A set of maintenance Step Functions creates new dataset import jobs on schedule; performs HAQM Personalize solution FULL retraining on schedule (and update associated campaigns); performs HAQM Personalize solution UPDATE retraining on schedule (and update associated campaigns); and creates batch inference jobs.
Step 9
Resource status notification updates are posted to an HAQM EventBridge event bus throughout the Step Functions workflow.
Step 10
A command line interface (CLI) allows you to import and establish schedules for resources that already exist in HAQM Personalize.
Step 1
The AWS CloudFormation template deploys an HAQM Simple Storage Service (HAQM S3) bucket used to store personalization data and configuration files.
Step 2
An AWS Lambda function initiated when new or updated personalization configuration is uploaded to the personalization data bucket.
Step 3
An AWS Step Functions workflow manages all of the resources of an HAQM Personalize dataset group (including datasets, schemas, event tracker, filters, solutions, campaigns, and batch inference jobs).
Step 4
HAQM CloudWatch metrics for HAQM Personalize for each new trained solution version are added to help you evaluate the performance of a model over time.
Step 5
An HAQM Simple Notification Service (HAQM SNS) topic and subscription notifies an administrator when the maintenance workflow has completed via email.
Step 6
HAQM DynamoDB tracks the scheduled events configured for HAQM Personalize to fully or partially retrain HAQM Personalize solutions, import or reimport datasets, and perform batch inference jobs.
Step 7
A Step Functions workflow tracks the current running scheduled events, and invoke step functions to perform HAQM Personalize solution maintenance (creating new solution versions, updating campaigns), import updated datasets, and perform batch inference.
Step 8
A set of maintenance Step Functions creates new dataset import jobs on schedule; performs HAQM Personalize solution FULL retraining on schedule (and update associated campaigns); performs HAQM Personalize solution UPDATE retraining on schedule (and update associated campaigns); and creates batch inference jobs.
Step 9
Resource status notification updates are posted to an HAQM EventBridge event bus throughout the Step Functions workflow.
Step 10
A command line interface (CLI) allows you to import and establish schedules for resources that already exist in HAQM Personalize.
Related content
This video shows you how to streamline and accelerate the development, automation, and deployment of your HAQM Personalize workloads using Maintaining Personalized Experiences with Machine Learning.
- Publish Date