Prediction integrations for time series deployments¶
Prediction integrations for time series deployments is off by default. Contact your DataRobot representative or administrator for information on enabling the feature.
Feature flag: Enable time series support for prediction integrations
To enable integration with a variety of enterprise databases, DataRobot provides a “self-service” platform to write predictions to databases. This allows you to select a data source to make predictions, define a schedule on which data is scored, and receive the results of predictions—all from a DataRobot deployment.
Now available as a public preview feature, you can configure prediction integration jobs for time series deployments. This requires additional configuration to the integration setup workflow.
Configuring time series deployment integrations¶
You must configure time series-specific settings to enable prediction integrations for time series deployments. Follow the workflow described here to integrate the desired database. After selecting the data source and configuring prediction options, complete the additional time series settings.
Choose the time series prediction method: forecast point or forecast range.
- Select forecast point to choose the specific date from which you want to begin making predictions. You can select the automatically determined forecast point (chosen by DataRobot based on the training dataset), or choose the point manually by using the date selector.
- Select forecast range if you intend to make predictions in larger batches. By default, predictions will use all forecast distances within the selected time range. Alternatively, you can specify a specific date range using the date selector.
Mark the checkbox if you want predictions to ignore "known in advance" features that would impact the prediction results.
Once you have configured the time series options for your integration, proceed with the remainder of the integration setup workflow.