SageMaker Canvas — re:Invent 2021
Less dependence on data engineering teams; build ML systems yourself
One of the first day announcement on the re:Invent 2021was Amazon SageMaker Canvas, a visual, no-code machine learning capability for business analysts that allows them to build ML models and generate accurate predictions without writing code or requiring ML expertise.
Amazon SageMaker Canvas is a visual point-and-click low code service, that makes it easy for business analysts to build ML models and generate accurate predictions without writing code or requiring ML expertise.
SageMaker Canvas makes it easy to seamlessly access and combine data from a variety of sources, automatically clean data and apply a variety of data adjustments, and create ML models to generate predictions with a single click. In addition, SageMaker Canvas easily publish results, explain and interpret models, and share models with others within the organization to improve productivity.
Amazon SageMaker uses AutoML technology to train models based on a given dataset.
SageMaker cleans and combines the data, creates hundreds of models, and selects the best one. Individual or batch predictions are generated
if you missed the talk you can find it here https://www.youtube.com/watch?v=8gm1TD9TXp0
BENEFITS OF USING SAGEMAKER CANVAS
- Generate ML predictions without writing code
- Amazon SageMaker is a fully managed service(serverless) to build, train, and deploy machine learning (ML) models for any use case with fully managed infrastructure, tools, and workflows.
- SageMaker Canvas is unique because it’s designed to break down silos across the machine learning pipeline by simply keeping data in a single platform and allowing stakeholders in the business to see and understand all the major stages of the machine learning modeling process.
- Like any no code solution this helps save time and reduce cost
- SageMaker Canvas leverages the same technology as Amazon SageMaker to automatically clean and combine the data, create hundreds of models under the hood
- Amazon SageMaker is designed for high availability. there are no maintenance windows or scheduled downtimes, with service stack replication configured across three facilities in each AWS region to provide fault tolerance
- Amazon SageMaker stores code in ML storage volumes, secured by security groups and optionally encrypted at rest.
- Amazon SageMaker does not use or share customer models, training data, or algorithms
- Validate ML models with data scientists
Easy and intuitive
Sagemaker Canvas is easy to learn. It has a very intuitive user interface you can browse and access disparate data sources over on-premises or in the cloud. It also combine datasets with just a click,
You then train accurate models and generate new predictions once new data is available.
- Fraud detection,
- churn reduction, use product consumption and purchase history data to uncover customer churn patterns and predict those at risk of churning in the future
- Multiple machine learning problem types are supported including binary and multi-class classifications, numerical regression, and time series forecasting.
- Optimize price and revenue
- Improve on-time deliveries
SageMaker Canvas is available today in US East (Ohio), US East (N. Virginia), US West (Oregon), Europe (Frankfurt), and Europe (Ireland).
payment based on for ML compute, storage, and data processing resources
the payment then is based on the resources used for hosting the notebook, training the model, performing predictions, and logging the outputs.
Amazon SageMaker allows you to select the number and type of instance used for the hosted notebook, training, and model hosting.
There are no minimum fees and no upfront commitments.