Skip to content

Click in-app to access the full platform documentation for your version of DataRobot.

Version 8.0.0

March 14, 2022

The DataRobot v8.0.0 release includes new time series features, described below. See also details of Release 8.0.0 in the AutoML and MLOps release notes.

New time series features

See details of the following new GA feature:

See details of the following public preview feature:

Generally available features

The following new features are now generally available.

Time series Predictor support in the AI App Builder

Now generally available, you can build AI-powered Predictor applications for both multi- and single-series projects. In your time series deployment, click the actions menu and select Create Application. Once created, upload batch predictions to populate the new Time Series widget, which allows you to navigate between multiple time unit resolutions, view calendar events (if uploaded), compare forecasted vs actual values for new data, and view insights for Prediction Explanations over time.

For details, see Time series Predictor applications.

Public preview features

The following features are part of the public preview program.

Scoring Code for time series

Scoring Code public preview capabilities for time series have expanded with this release, bringing Scoring Code support for:

Note

If you want Scoring Code support for a project using calendars and your calendar has only full-day events (such as holidays), ask your platform administrator to enable the Disable High-Resolution Calendars for Time Series Projects feature flag for your account.

Time series parameters for CLI scoring

DataRobot supports using scoring at the command line for time series deployments. You can now specify the time series parameters for forecast point, date format, prediction start and end dates, and prediction intervals.

Scoring Code for segmented modeling

With segmented modeling, you can build individual models for segments of a multiseries project. DataRobot then merges these models into a Combined Model. Now you can generate Scoring Code for the Combined Model.

To generate Scoring Code, each segment champion of the Combined Model must have Scoring Code:

After you deploy the Combined Model, download Scoring Code as normal.

Prediction intervals in Scoring Code

You can now include prediction intervals in the downloaded Scoring Code JAR for a time series model. To include prediction intervals in your Scoring Code JAR, in your deployment, click Predictions > Portable Predictions and select Scoring Code. Toggle on Include prediction intervals.

For more details on the time series Scoring Code features, see Scoring Code for time series projects.


Updated July 20, 2022
Back to top