Lab - Monitor a Model for Data Drift

In this lab, you create a production endpoint with data capture activated, generate baseline statistics and constraints, create a SageMaker Model Monitor baseline processing job, set up CloudWatch alarms for SageMaker Model Monitor, view model performance, and start an automated workflow to retrain the model.

Objectives:

• Activate data capture for a real-time endpoint.
• Generate baseline statistics and constraints.
• Create a SageMaker Model Monitor baseline processing job./li>
• Set up alerts and notification for data drift.
• Start an automatic model retraining workflow.

Prerequisites:

• Basic navigation of the AWS Management Console
• Basic familiarity with Machine Learning concepts

Outline:

• Task 1: Set up the environment
• Task 2: Model monitoring
• Task 3: Review the automatic model retraining workflow