AWS Brings Codelessness to Amazon SageMaker Machine Learning

Amazon Web Services announced limited general availability of Amazon SageMaker Canvas, a codeless visual tool for creating machine learning models for business analysts.

Designed as a new capability for the Amazon SageMaker machine learning service, SageMaker Canvas provides a visual interface that accesses data from disparate sources and prepares the data for training machine learning (ML) models. A point-and-click interface helps generate accurate ML predictions without requiring ML experience or writing code. SageMaker Canvas is integrated with Amazon SageMaker Studio.

Amazon SageMaker uses AutoML technology to train models based on a given set of data. SageMaker cleans and combines data, creates hundreds of models and selects the best. Individual or batch predictions are generated. Use cases can be addressed, such as fraud detection, churn reduction and inventory optimization. Several types of machine learning problems are supported, including binary and multiclass classifications, numerical regression, and time series forecasting.

Data is accessible from cloud-based and on-premises data sources. SageMaker Canvas corrects data errors and analyzes data readiness for ML. But as of November 30, SageMaker Canvas was only available in Oregon, Ohio, and Northern Virginia in the US, and Frankfurt, Germany, and Ireland.

AWS also unveiled this week a preview of Amazon SageMaker Studio Lab, a free service to experience ML. Amazon SageMaker Studio Lab is based on open source Jupyterlab notebook and provides free access to AWS compute resources.

Copyright © 2021 IDG Communications, Inc.

Comments are closed.