Posted On: Jun 7, 2023

Amazon SageMaker Canvas now provides the ability to retrain machine learning (ML) models and automate batch prediction workflows with updated datasets thereby making it easier to constantly learn and improve the model performance and drive efficiency. SageMaker Canvas is a visual interface that enables business analysts to generate accurate ML predictions on their own — without requiring any ML expertise or having to write a single line of code. 

An ML model's effectiveness depends on the quality and relevance of the data it's trained on. As time progresses, the underlying patterns, and distributions in the data may change. By updating the dataset, you ensure that the model learns from the most recent data, thereby improving its ability to make accurate predictions. Starting today, you can automatically and manually update datasets (local upload and Amazon S3 only) in SageMaker Canvas and train ML models on the latest version of the dataset. 

After the model is trained, you may want to run predictions on it. Running batch predictions enables processing multiple data points simultaneously instead of making predictions one by one. Until now, SageMaker Canvas only supported running manual batch predictions on ML models. You can now automate batch prediction workflows with new incoming data which brings efficiency, scalability and reliability to your prediction process. After training an ML model you can set up an automated batch prediction configuration and associate a dataset to it. When the dataset is updated, either manually or on a schedule, the configured batch prediction workflow will get triggered automatically. Results of the predictions can be viewed in the app or downloaded for later review. 

The ability to update datasets and automate batch predictions in Amazon SageMaker Canvas 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.