Amazon SageMaker Canvas

Build highly accurate ML models using a visual interface, no code required

Why SageMaker Canvas?

Through a no-code interface, you can create highly accurate machine learning models —without any machine learning experience or writing a single line of code. SageMaker Canvas provides access to ready-to-use models including foundation models from Amazon Bedrock or Amazon SageMaker JumpStart or you can build your own custom ML model. With SageMaker Canvas, you can easily access and import data from 50+ sources, prepare data using natural language and 300+ built-in transforms, build and train highly accurate models, generate predictions, and deploy models to production.

Amazon SageMaker Canvas Overview (1:11)

Ready-to-Use Models

  • Foundation models
  • Foundation Models

    Foundation Models

    SageMaker Canvas provides access to ready-to-use foundation model (FMs) such as Claude 2, Amazon Titan, and Jurassic-2 (powered by Amazon Bedrock) as well as publicly available FMs such as Falcon and MPT (powered by SageMaker JumpStart)

  • Tabular, CV, and NLP models
  • Tabular, CV, and NLP models

    Tabular, CV, and NLP models

    SageMaker Canvas provides access to ready to use tabular, NLP, and CV models powered by AWS AI services, including Amazon Rekognition, Amazon Textract, and Amazon Comprehend.

Custom Models

  • Data Preparation
  • Data preparation

    Data Preparation

    SageMaker Canvas offers no-code data exploration and preparation through a point-and-click or natural language UI.

  • Build Models
  • Build Models

    Build Models

    SageMaker Canvas uses Amazon’s AutoML to build a custom model trained on your dataset.

  • Evaluate Models
  • Model Status Graph

    Evaluate Models

    SageMaker Canvas helps you understand model performance with common evaluation metrics and visuals.

  • Use Models
  • Use Models

    Use Models

    You can generate predictions in the SageMaker Canvas UI or deploy to a SageMaker endpoint.

Benefits of SageMaker Canvas

Amazon SageMaker Canvas provides a visual point-and-click interface for business analysts to solve business problems using ML such as customer churn prediction, fraud detection, forecasting financial metrics and sales, inventory optimization, content generation, and more without writing any code.
Amazon SageMaker Canvas provides access to ready-to-use foundation model (FMs) for content generation, text extraction, text summarization, document summarization and Q&A, sentiment analysis, object detection, text detection, and more. You can access and tune FMs such as Claude 2, Amazon Titan, and Jurassic-2 (powered by Amazon Bedrock) as well as publicly available FMs such as Falcon and MPT (powered by SageMaker JumpStart) without writing any code.
Amazon SageMaker Canvas supports the full ML lifecycle including data import from 50+ data sources, comprehensive data preparation with 300+ built-in transforms and using natural language queries to explore and prepare data, building your own custom models with advanced training options, generating and automating predictions for what-if scenarios and batch inference, and deploying models to real-time endpoints.
Amazon SageMaker Canvas boosts collaboration between business analysts and data science teams. All models created in Amazon SageMaker Canvas can be shared, reviewed, and updated with data scientists through SageMaker Studio. In addition, models and predictions can be shared with business analysts through Amazon QuickSight.

Use Cases

Create personalized, engaging, and high-quality sales and marketing content such as social media posts, product descriptions, and email campaigns.
Produce concise summaries of articles, blog posts, and documents to identify the most important information, highlight key takeaways, and more quickly distill information.

Analyze and extract information from a variety of documents, such as insurance claims, invoices, expense reports, or identity documents.

Use product consumption and purchase history data to uncover customer churn patterns and predict those at risk of churning in the future.

Forecast inventory levels by combining historical sales and demand data with associated web traffic, pricing, product category, and holiday data