Amazon SageMaker Autopilot adds support for time series data
Amazon SageMaker Autopilot automatically builds, trains, and tunes the best machine learning models based on your data, while allowing you to maintain full control and visibility. Starting today, SageMaker Autopilot supports time series data. You can now use SageMaker Autopilot to build machine learning models for regression and classification problems for time series data or any sequence data, enabling scenarios such as supervised anomaly detection, risk assessment or fault prediction based on a sequence of datapoints. For example, you can now build models to identify and classify anomalous network traffic recorded over time, or identifying faulty devices based on emitted metrics.
Amazon SageMaker Autopilot automatically builds, trains, and tunes the best machine learning models based on your data, while allowing you to maintain full control and visibility. Starting today, SageMaker Autopilot supports time series data. You can now use SageMaker Autopilot to build machine learning models for regression and classification problems for time series data or any sequence data, enabling scenarios such as supervised anomaly detection, risk assessment or fault prediction based on a sequence of datapoints. For example, you can now build models to identify and classify anomalous network traffic recorded over time, or identifying faulty devices based on emitted metrics.
You can get started with automatically building machine learning models with time series data by simply including the time series data in your input tabular dataset for SageMaker AutoPilot. SageMaker Autopilot will automatically parse this data, extract meaningful features, and test multiple ML algorithms to process it. Support for time series data is available in all AWS regions where SageMaker Autopilot is currently supported. For more details, please review documentation. To get started with SageMaker Autopilot, see the product page or access SageMaker Autopilot within SageMaker Studio.