Set up humility rules¶

MLOps allows you to create humility rules for deployments on the Settings > Humility tab. Humility rules enable models to recognize, in real time, when they make uncertain predictions or receive data they have not seen before. Unlike data drift, model humility does not deal with broad statistical properties over time—it is instead triggered for individual predictions, allowing you to set desired behaviors with rules that depend on different triggers. Using humility rules to add triggers and corresponding actions to a prediction helps mitigate risk for models in production. Humility rules help to identify and handle data integrity issues during monitoring and to better identify the root cause of unstable predictions.

The Settings > Humility tab contains the following sub-tabs:

• Settings: Create humility rules to monitor for uncertainty and specify actions to manage it.

• Prediction Warnings (for regression projects only): Configure prediction warnings to detect when deployments produce predictions with outlier values.

Specific humility rules are available for multiseries projects. While they follow the same general workflow for humility rules as AutoML projects, they have specific settings and options.

Create humility rules¶

To create humility rules for a deployment:

1. On the Dashboard, open a deployment and navigate to the Settings > Humility tab.

2. On the Humility Rules Settings page, if you haven't enabled humility for a model, click the Enable humility toggle, then:

   

   • To create a new, custom rule, click + Add Rule.

   • To use the rules provided by DataRobot, click + Use Recommended Rules. This option generates two automatically configured humility rules:

     • Rule 1: An Uncertain prediction trigger and No operation action.

     • Rule 2: An Outlying input trigger, for the most important numeric feature based on Feature Impact results, and No operation action.

     Both recommended rules have automatically calculated upper- and lower-bound thresholds.

3. Click the pencil icon () to enter a name for the rule, then, select a Trigger and an Action to take based on the selected trigger. The trigger detects a rule violation and the action handles the violating prediction. The trigger and action selection process differs for multiseries models:

   Standard workflowMultiseries workflow

   • Select a Trigger for the rule you want to create. Each trigger requires specific settings. The following table and subsequent sections describe these settings. There are three triggers available:

     

     Trigger	Description	To configure
     Uncertain prediction	Detects whether a prediction's value violates the configured thresholds based on lower-bound and upper-bound thresholds for prediction values.	Enter values either manually or click Calculate to use computed thresholds derived from the Holdout partition of the model (DataRobot models only). For regression models, the trigger detects any values outside of the configured thresholds. For binary classification models, the trigger detects any prediction's probability value that is inside the thresholds. You can view the type of model for your deployment from the deployment's Overview tab.
     Outlying input	Detects if the input value of a numeric feature is outside of the configured thresholds.	Select a numeric feature and set the lower-bound and upper-bound thresholds for its input values. Enter the values manually or click Calculate to use computed thresholds derived from the training data of the model (DataRobot models only).
     Low observation region	Detects if the input value of a categorical feature value is not included in the list of specified values.	Select a categorical feature and indicate one or more values. Any input value that appears in prediction requests that does not match the indicated values triggers an action.

   • Select an Action for the rule you are creating. DataRobot applies the action if the trigger indicates a rule violation. There are three actions available:

     Action	Description	To Configure
     Override prediction	Modifies predicted values for rows violating the trigger with the value configured by the action.	Set a value that will overwrite the returned value for predictions violating the trigger. For binary classification and multiclass models, the indicated value can be set to either of the model's class labels (e.g., "True" or "False"). For regression models, manually enter a value or use the maximum, minimum, or mean provided by DataRobot (DataRobot models only).
     Throw error	Rows in violation of the trigger return a 480 HTTP error with the predictions, which also contributes to the data error rate on the Monitoring > Service health tab.	Use the default error message provided or specify your own custom error message. This error message will appear along a 480 HTTP error with the predictions.
     No operation	No changes are made to the detected prediction value.	No configuration needed.

   DataRobot supports multiseries blueprints that support feature derivation and predictions using partial history or no history at all—series that were not trained previously and do not have enough points in the training dataset for accurate predictions. This is useful, for example, in demand forecasting. When a new product is introduced, you may want initial sales predictions. In conjunction with “cold start modeling” (modeling on a series in which there is not sufficient historical data), you can predict on new series, but also keep accurate predictions for series with a history. With the support in place, you can set up a humility rule that triggers on a new series (unseen in training data), takes a specified action, and, optionally, returns a custom error message. To do this, take the following steps:

   • Select a Trigger. To include new series data, select New series as the trigger. This rule detects if a series is present that was not available in the training data and does not have enough history in the prediction data for accurate predictions.

   • Select an Action. Subsequent options are dependent on the selected action, as described in the following table:

     

     Action	If a new series is encountered...	Further action
     No operation	DataRobot records the event but the prediction is unchanged.	N/A
     Use model with new series support	The prediction is overridden by the prediction from a selected model with new series support.	Select a model that supports unseen series modeling. DataRobot preloads supported models in the dropdown.
     Use global most frequent class (binary classification only)	The prediction value is replaced with the most frequent class across all series.	N/A
     Use target mean for all series (regression only)	The prediction value is overridden by the global target mean for all series.	N/A
     Override prediction	The prediction value is changed to the specified preferred value.	Enter a numeric value to replace the prediction value for any new series.
     Return error	The default or a custom error is returned with the 480 error.	Use the default or click in the box to enter a custom error message.

   If you select Use model with new series support, when you expand the Model with new series support dropdown, DataRobot provides a list of models available from the Registry, not from Workbench. Using models available from the registry decouples the model from the Use Case and provides support for packages. In this way, you can use a backup model from any compatible Use Case as long as it uses the same target and has the same series available.

   Note

   If you replace a model within a deployment using a model from a different Use Case, the humility rule is disabled. If the replacement is a model from the same Use Case, the rule is saved.

   When rule configuration is complete, a rule explanation displays below the rule describing what happens for the configured trigger and respective action.

4. Click Add to save the rule, and click +Add new rule to add additional rules.

5. After adding rules, click Submit.

   Warning

   Clicking Submit is the only way to permanently save new rules and rule changes. If you navigate away from the Humility tab without clicking Submit, your rules and edits to rules are not saved.

   Note

   If a rule is a duplicate of an existing rule, you cannot save it. In this case, when you click Submit, a warning displays:

   After you save and submit the humility rules, DataRobot monitors the deployment using the new rules and any previously created rules. After a rule is created, the prediction response body returns the humility object. Refer to the Prediction API documentation for more information.

Manage humility rules¶

You can edit or delete existing rules from the Humility > Rules tab if you have owner permissions:

After managing the humility rules, click Submit. If you navigate away from the Humility tab without clicking Submit, your changes will be lost.

Humility rules considerations¶

Consider the following when using Humility rules:

• You cannot define more than 10 humility rules for a deployment.

• Humility rules can only be defined by owners of the deployment. Users of the deployment can view the rules but cannot edit them or define new rules.

• The "Uncertain Prediction" trigger is only supported for regression and binary classification models.

• Multiclass models only support the "Override prediction" trigger.