Bring ML models built anywhere into Amazon SageMaker Canvas and generate predictions
You can now bring machine learning (ML) models built anywhere into Amazon SageMaker Canvas and generate predictions, to address a wide range of business problems. SageMaker Canvas is a visual interface that enables business analysts to generate accurate ML predictions on their own — without requiring any ML experience or having to write a single line of code.
You can now bring machine learning (ML) models built anywhere into Amazon SageMaker Canvas and generate predictions, to address a wide range of business problems. SageMaker Canvas is a visual interface that enables business analysts to generate accurate ML predictions on their own — without requiring any ML experience or having to write a single line of code.
Today, hundreds of ML models are built and trained using different tools and in heterogeneous environments. Quite often, business teams could benefit from ML models already built by data scientists to solve business problems, rather than starting from scratch. However, it is not easy to use these models outside the environments they are built in due to stringent technical requirements, rigidity of tools, and manual processes to import models. This forces users to often rebuild ML models resulting in duplication of efforts, spending additional time and resources, and limiting democratization of ML.
Amazon SageMaker Canvas removes these limitations and the heavy lifting needed to import models between environments. Starting today, data scientists can now share ML models built anywhere with business analysts in SageMaker Canvas, so predictions can be generated on those models directly in SageMaker Canvas. ML models using tabular data and built anywhere can be imported into SageMaker Canvas once they are registered in the Amazon SageMaker Model Registry. Additionally, data scientists can share models trained in Amazon SageMaker Autopilot and Amazon SageMaker JumpStart so business analysts can generate predictions on those models in SageMaker Canvas. Finally, you can now share models built in SageMaker Canvas with data scientists using SageMaker Studio for review, update, and feedback. Data scientists can then share their feedback or updates with you, so you can analyze and generate predictions on updated model versions within SageMaker Canvas.
The ability to generate predictions in Amazon SageMaker Canvas on imported models built anywhere is now available in all AWS regions where SageMaker Canvas is supported. To learn more, refer to the AWS News Blog and SageMaker Canvas product documentation.