Q: What is Amazon SageMaker Canvas?

Amazon SageMaker Canvas is a visual, point-and-click service that allows business analysts to generate accurate machine learning (ML) predictions without writing any code or requiring ML expertise. SageMaker Canvas makes it easy to access and combine data from a variety of sources, automatically clean data and apply a variety of data adjustments, and build ML models to generate accurate predictions with a single click. You can also easily publish results, explain and interpret models, and share models with others within your organization to review.

Q: How do I get started with Amazon SageMaker Canvas?

You can access Amazon SageMaker Canvas through the AWS Management console by creating a SageMaker Domain and launching SageMaker Canvas. After setting up SageMaker Canvas in the console, you or your IT administrator can also configure single sign-on (SSO) to enable users to launch SageMaker Canvas without accessing the console.
Once you log into SageMaker Canvas, you can try the interactive product tour that walks you through each step of the ML journey with easy-to-follow directions. Additionally, you can use sample datasets provided in SageMaker Canvas to help you get started with common use cases such as house price prediction, sales forecasting, predicting loan defaults, and more. These datasets can be used to get you familiar with building and training ML models with SageMaker Canvas before you use your own data.
Q: Which SSO techniques are supported by Amazon SageMaker Canvas?
All SAML (Security Assertion Markup Language) 2.0 enabled SSO techniques are supported by Amazon SageMaker Canvas. Examples include AWS SSO, Active Directory, and Okta.

Q: What data sources does Amazon SageMaker Canvas support?

SageMaker Canvas enables you to seamlessly discover AWS data sources that your account has access to, including Amazon Simple Storage Service (S3) and Amazon Redshift. You can browse and import data using the SageMaker Canvas visual, point-and-click interface. Additionally, you can drag and drop files from your local disk, and use pre-built connectors to import data from third-party sources such as Snowflake.

Q: What data types does Amazon SageMaker Canvas support?

Currently, SageMaker Canvas supports the following data types: Categorical, Numeric, Text, and DateTime. This enables you to work with tabular and time series data for your ML use cases.

Q. How can I analyze and explore my data?

SageMaker Canvas allows you to analyze and explore your data through data transformations such as filtering rows, extracting values from columns, replacing values with standard values such as mean or median or custom values, and filtering outliers. Additionally, you can add new features to your data using mathematical functions through custom formulas or using logical operators to create data bins.

SageMaker Canvas offers visualizations including scatter plots, bar charts, and box plots to visually explore your data. SageMaker Canvas also offers the support to build correlation matrices to understand the relationships between data variables for both numeric and categorical data.

Q: In what regions is Amazon SageMaker Canvas available?

Amazon SageMaker Canvas is available in the US East (Ohio), US East (N. Virginia), US West (Oregon), Europe (Frankfurt), Europe (Ireland), Asia Pacific (Mumbai), Asia Pacific (Seoul), Asia Pacific (Singapore), Asia Pacific (Tokyo), and Australia (Sydney) AWS Regions.
Q: How do I build an ML model to generate predictions?
Once you have connected to data sources, selected a dataset, and prepared your data, you can select the target column that you want to predict to initiate a model creation job. Amazon SageMaker Canvas will automatically identify the problem type, generate new relevant features, test a comprehensive set of prediction models using ML techniques such as linear regression, logistic regression, deep learning, time series forecasting, and gradient boosting, and build the model that makes accurate predictions based on your dataset. You can also choose Preview Model to understand how the model will make predictions. The prediction accuracy is an indicator of the the model value.

Q: How can I validate my data to confirm it is ready to build a model?

Amazon SageMaker Canvas provides an option to validate your data prior to model building to check for common data issues such as invalid characters and missing values. SageMaker Canvas highlights these issues with a pointer to fix these issues before building ML models.

Q. How can I encrypt my data and ML models with SageMaker Canvas?

SageMaker Canvas supports encryption at rest for datasets and ML models using customer managed keys (CMK) with AWS Key Management Service (KMS) for all use cases including classification, regression, and time-series forecast. You can use your own keys to encrypt the file systems on the instances used to train models and generate insights, and the model data in your Amazon S3 bucket.

Q: How long does it take to build a model?

The time it takes to build a model depends on the size of your dataset and selected build mode. Small datasets can take less than 5 minutes, and large datasets can take a few hours. As the model building progresses, Amazon SageMaker Canvas provides updates and estimated time to completion.

Amazon SageMaker Canvas provides multiple options to build a model.

  • Preview: This option lets you preview your model in about 2 minutes to give you an indicator of the model accuracy and feature importance.
  • Quick Build: This option allows you to build a model quickly (approximately between 2 and 15 minutes) and provides a ready-made model.
  • Standard Build: This option is extensive and may take a few hours depending on the size of your dataset. Standard build models provide you with detailed information including metric scores, training experiments using different combinations of hyperparameters, and generates multiple models in the backend. It then picks the best model that you can evaluate and use.

Q: How do I make predictions?

To make a single prediction, go to the “single prediction” tab, input values, and Amazon SageMaker Canvas will show you the prediction. You can also use sliders and pull-down menus to change input values to see the impact on the prediction. To make predictions for multiple observations or rows of data, go to the “bulk prediction” tab, drag and drop the CSV file containing your observation, and SageMaker Canvas will create a new CSV file with predictions.

Q: How can I explain my model to others?

Amazon SageMaker Canvas provides column impact analysis which explains the impact that each column in your dataset has on a model. SageMaker Canvas also provides additional metrics that provide visibility into model performance. Additionally, when you generate predictions, you can see the column impact that identifies which columns have the most impact on each prediction.

Q: How am I charged for Amazon SageMaker Canvas?

With SageMaker Canvas, you are charged on a pay-as-you-go model with usage based pricing. There are two components that determine your charges for using SageMaker Canvas.

  • Session charges: This is based on the number of hours you are logged into SageMaker Canvas or using SageMaker Canvas. A session starts when you launch the SageMaker Canvas application, and ends when you log out.
  • Training charges: This is based on the size of your dataset to train your model. You pay based on the number of cells that is calculated by measuring the number of columns by the number of rows in your dataset.

See the SageMaker Canvas pricing page for details.

Q: How do I log out of Amazon SageMaker Canvas?

You can log out of SageMaker Canvas by clicking on your account at the bottom of the left navigation panel. Alternatively, your administrator can log you out through the AWS console. Session charges will be stopped once you log out.


Q: Can I share models built in Amazon SageMaker Canvas with data scientists and collaborate with them?

Yes. You can share ML models built in SageMaker Canvas with data scientists working in SageMaker Studio. Data scientists can review, update, and share updated model versions with you, so you can generate predictions on the new versions in SageMaker Canvas.

After building and training a standard model in SageMaker Canvas, you can share your ML model using the share button in SageMaker Canvas. You can choose to share the model to a single user or multiple users within SageMaker Studio.

Q: Which ML model artifacts can be shared from SageMaker Canvas to SageMaker Studio?

The ML model and artifacts shared from SageMaker Canvas will contain the dataset, data transformations (including the recipe data flow and transformation code), list of candidate models and the recommended model, data exploration report, candidate definition notebook, and explainability metrics (including feature importance).

Q: Which artifacts can be edited and updated by data scientists?

Data scientists using SageMaker Studio can view model artifacts and recommend an alternate candidate from the list of candidates in SageMaker Autopilot. In addition, they can open and update data transformations with SageMaker Data Wrangler, update the model using SageMaker Autopilot, and share the new model version.

Q: How can SageMaker Studio users update models they receive from SageMaker Canvas?

SageMaker Studio users can send updates on model versions using the share button within SageMaker Studio. The updated model from SageMaker Studio will appear as a new version of the original shared model directly in SageMaker Canvas.

Q: How can I distinguish between my original shared model and a new shared model?

Updated models are automatically versioned within SageMaker Canvas. You can access different versions of the model through the drop-down menu within SageMaker Canvas.

Q: What use cases and model types can I share from SageMaker Canvas to SageMaker Studio?

You can share standard build models containing tabular data for all use cases within SageMaker Canvas, including customer churn, predicting home prices, sales forecasting, predicting loan defaults, predicting hospital bed occupancy, and time-series forecasting models.

Bring your own ML model

Q: Can data scientists share models built outside of SageMaker so I can generate predictions on those models in SageMaker Canvas?

Yes. Data scientists can share any ML model built by other tools once it is registered in the SageMaker Model Registry, allowing you to generate predictions on these models in SageMaker Canvas. Data scientists can also share models originated within SageMaker, including from SageMaker Autopilot and SageMaker JumpStart, so you can generate predictions on these models directly in SageMaker Canvas.

Q: How can I discover shared models within SageMaker Canvas?

Shared models are accessible through the SageMaker Canvas models page.

Q: How can I discover shared models within SageMaker Studio?

Shared models are accessible through the shared models and notebooks page in SageMaker Studio.

Amazon SageMaker Canvas pricing
Learn more about Amazon SageMaker Canvas Pricing

Get started with Amazon SageMaker Canvas with no upfront commitments or long-term contracts.

Learn more 
Sign up for an AWS account
Sign up for a free account

Instantly get access to the AWS Free Tier. 

Sign up 
Start building in the console
Start building in the console

Get started building with Amazon SageMaker Canvas in the AWS Management Console.

Sign in