Machine learning (ML) models have become key drivers in helping organizations reveal patterns and make predictions that drive value across the business. While extremely valuable, building and deploying these models remains in the hands of only a small subset of expert data scientists and engineers with deep programming and ML framework expertise.

But what if you could unblock analysts that have strong business acumen and SQL expertise to further embed machine learning in more parts of the organization? The Snowflake integration with Amazon SageMaker Autopilot can do that by combining Snowflake’s access to data with the automated machine learning (AutoML) capabilities of Amazon SageMaker Autopilot to effortlessly build and deploy ML models using SQL from inside Snowflake. We are very excited to announce this native integration is now available in public preview and takes part in the AWS initiative “AI for data analytics” (AIDA).  

“Using the Snowflake and Amazon SageMaker Autopilot integration, teams can simplify the effort of transforming data into ML-powered insights, expanding the power of data science beyond the immediate data science teams,” said Torsten Grabs, Director of Product Management at Snowflake. “Customers such as Western Union that tailor their customers’ digital banking experiences through propensity and segmentation models will be able to hyper-personalize those experiences with more-granular models. This will reduce the heavy lift associated with building ML models and can lower operating costs through the automation of training and deploying state-of-the-art machine learning models from within Snowflake.”

With the native integration, analysts and other SQL users will be able to leverage the power of SageMaker Autopilot to build and deploy models using their tabular data sets in Snowflake for a wide range of use cases that use regression and classification algorithms. This includes popular sales and marketing use cases such as customer churn prediction, customer lifetime value, price and sales predictions, as well as industry-specific use cases such as predictive maintenance.  

To show you just how easy it is to get started, we have built a Quickstart guide on building and deploying an ML model using SQL. It covers:

  • Prerequisites
  • Three simple steps for the one-time setup process
  • Snowflake SQL functions for AutoML using SageMaker Autopilot
    • Start training: aws_autopilot_create_model ()
    • Status checks: aws_autopilot_describe_model()
    • Get predictions: aws_autopilot_predict_outcome()
  • Model optimization ideas

Get started on quickstarts.snowflake.com