AIM357 - Build an ETL pipeline to analyze customer data

Machine learning involves more than just training models; you need to source and prepare data, engineer features, select algorithms, train and tune models, and then deploy those models and monitor their performance in production. Learn how to set up an ETL pipeline to analyze customer data using Amazon SageMaker, AWS Glue, and AWS Step Functions.

This workshop will be around the ETL and full pipeline to perofrm Time-series forecasting using NYC Taxi Dataset. It includes the following steps:

  • Crawl, Discover, and Explore the new datasets in a Data lake
  • Perform Extract, Transform, Load (ETL) jobs to clean the data
  • Train a Machine Learning model and run inference
  • Assess the response
  • Send an alert if value is outside specified range

The workshop uses the following architecture:


Steps for launching the workshop environment using EVENT ENGINE

open a browser and navigate to

Enter a 12-character “hash” provided to you by workshop organizer.

Click on “Accpet Terms & Login”

Navigate to Sagemaker Service

Click on “AWS Console”

Navigate to Sagemaker Service

Please, log off from any other AWS accounts you are currently logged into

Click on “Open AWS Console”

Navigate to Sagemaker Service