Amazon recently announced the general availability of Amazon SageMaker Canvas, a new visual, no code capability that allows business analysts to build ML models and generate accurate predictions without writing code or requiring ML expertise. Its intuitive user interface lets users browse and access disparate data sources in the cloud or on-premises, combine datasets with the click of a button, train accurate models, and then generate new predictions once new data is available.
SageMaker Canvas leverages the same technology as previous Amazon SageMaker to automatically clean and combine data, create hundreds of models under the hood, select the one performing best, and generate new individual or batch predictions.
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, a capability that was not available prior.
Users can use any dataset, from high complexity and down to a basic CSV file, and then decide which of the columns in this dataset Canvas should predict. Data can be imported or fetched from Amazon Simple Storage Service (Amazon S3) or connected to other cloud or on-premises data sources, such as Amazon Redshift or Snowflake.
Training the created model is not to be worried about, as SageMaker Canvas shows the value distribution and already recommends the most appropriate model type. Before proceeding with the model training, SageMaker Canvas also provides the option to generate an analysis report. The model, when ready, lets analyze its accuracy and the column impacts visually through the console. The Amazon SageMaker Studio integration lets share the model easily with other data scientists in a team. This makes for a far easier user experience than using traditional ML tools.
SageMaker Canvas is now generally available in US East (Ohio), US East (N. Virginia), US West (Oregon), Europe (Frankfurt), and Europe (Ireland). Users can start using it with local datasets, as well as data already stored on Amazon S3, Amazon Redshift, or Snowflake. With just a few clicks, users can prepare and join datasets, analyze estimated accuracy, verify which columns are impactful, train the best performing model, and generate new individual or batch predictions.