No-Code Machine Learning Services for AWS

Amazon has today announced Amazon SageMaker Canvas, a new machine learning service. The target audience here isn’t high-tech data scientists and engineers, but rather anyone working in a company with access to IT resources.

SageMaker Canvas promises to make it possible for anybody with little or no technical expertise to build machine learning prediction models using an easy-to-use graphical interface.

If that sounds familiar, it’s probably because Azure and other providers offer comparable technologies, although AWS may have the upper hand since many businesses already save all of their data in AWS.

“SageMaker Canvas leverages the same technology as Amazon SageMaker to automatically clean and combine your data, create hundreds of models under the hood, select the best performing one, and generate new individual or batch predictions,” writes AWS’s Alex Casalboni in today’s announcement.

“It supports multiple problem types such as binary classification, multi-class classification, numerical regression, and time series forecasting. These problem types let you address business-critical use cases, such as fraud detection, churn reduction, and inventory optimization, without writing a single line of code.”

The service is powered by SageMaker, AWS’eifully managed machine learning service. Users may choose which of the columns in a dataset Canvas should predict by using any data file, down to a simple CSV file.

There’s no need to be concerned about how to train this model. We’re not yet talking drag-and-drop, though, since we’re still on AWS. The overall experience is more like working in the AWS console than a modern no-code application.