Skip to content

On-premise users: click in-app to access the full platform documentation for your version of DataRobot.

Deployment settings

The deployment settings tabs enable and configure capabilities of your current deployment based on the data provided, for example, training data, prediction data, or actuals. After you create and configure a deployment, you can use the deployment settings to add or update deployment functionality that wasn't configured during deployment creation.

Topic Describes how to
Set up service health monitoring Enable segmented analysis to assess service health, data drift, and accuracy statistics by filtering them into unique segment attributes and values.
Set up data drift monitoring Enable data drift monitoring to monitor both target and feature drift information.
Set up accuracy monitoring Enable accuracy monitoring to analyze the performance of the model deployment over time.
Set up fairness monitoring Enable fairness monitoring to identify any biases in a binary classification model's predictive behavior.
Set up custom metrics monitoring Enable custom metrics monitoring by defining the "at risk" and "failing" thresholds for the custom metrics you created.
Set up humility rules Enable humility monitoring by creating rules that enable models to recognize, in real-time, when they make uncertain predictions or receive data they have not seen before.
Configure challengers Enable challenger comparison by configuring a deployment to store prediction request data at the row level and replay predictions on a schedule.
Configure retraining Enable Automated Retraining for a deployment by defining the general retraining settings and then creating retraining policies.
Configure predictions settings Review the Predictions Settings tab to view details about your deployment's prediction data or, for deployed time series models, enable prediction intervals in the prediction response.
Set up timeliness tracking Enable timeliness tracking for predictions and actuals on the Usage Settings tab; define the timeliness interval frequency based on the prediction timestamp and the actuals upload time separately, depending on your organization's needs.
Configure data exploration Enable data exploration to compute and monitor custom business or performance metrics.
Configure deployment notifications Enable personal notifications to trigger emails for service health, data drift, accuracy, and fairness monitoring.
Configure deployment resource settings For custom model deployments, view the custom model resource settings defined during custom model assembly. If the custom model is deployed on a DataRobot Serverless prediction environment and the deployment is inactive, you can modify the resource bundle settings.

Updated October 24, 2024