Adaptive Models Management landing page

Use the Adaptive Models facilities to manage the adaptive models specific to your application. Models in the ADM system are the result of executing a strategy that contains adaptive model components. An adaptive model component references the adaptive model rule that configures how the model is created, how it learns and how it predicts behavior.

Access this landing page by selecting the > Decisioning > Predictive Analytics > Adaptive Models Management menu item.

When opening this landing page, Pega 7 checks the status of the UpdateAdaptiveModels agent. If the agent is not running, go to the Services landing page and press Start Agent.

Click Show last responses to open the Last Responses Overview dialog showing response model and predictor information for the last five records sent to the ADM database. You can use the information provided in this dialog to troubleshoot the learning process by:

• Checking if response information contains the data required by the predictors.
• Checking response information that has not been factored in the ADM system (for example, responses that have not been taken into account because the process of running data analysis was not triggered).

The overview of adaptive models shows the information pertaining to every adaptive model. The information displayed in the overview depends on the configuration of adaptive models and how each adaptive model component is defined in the strategy:

• Business Issue: the issue in the decision hierarchy.
• Group: the group in the decision hierarchy.
• Proposition: the name of the proposition the adaptive model is modeling.
• Direction: the direction.
• Channel: the channel.
• Rule: the name of the adaptive model rule that configures the adaptive model.
• Applies To: the Applies To class of the adaptive model rule.
• Responses: the number of responses.
• Performance: the model performance.

For each model, actions are available to manage the adaptive statistics, view model settings and train models.

• Clear Model
• Delete Model
• View Model Parameters
• Upload Responses

Available in applications that have access to the Decision Management rule sets or in applications built on PegaDM.

Clear Model

This action lets you remove all the adaptive statistics associated with the adaptive model. In this process, everything is cleared, including numeric predictors boundaries.

To clear models:

1. Locate the model for which you want remove the adaptive statistics.
2. In the Actions menu, select Clear Model to open the Clear Adaptive Model dialog.
3. Click Clear to remove the adaptive statistics in the ADM system. By default, the associated records in the ADM Data Mart are also deleted, but you can change this setting by deselecting the data mart records option.

Delete Model

This action lets you delete the current model. If used by a strategy, the model is recreated again when the strategy is executed. Deleting models implies the loss of the adaptive statistics associated with that model.

To delete models:

1. Locate the model you want to delete.
2. In the Actions menu, select Delete Model to open the Delete Adaptive Model dialog.
3. Click Delete to remove the model from the ADM system. By default, the associated records in the ADM Data Mart are also deleted, but you can change this setting by deselecting the data mart records option.

View Model parameters

Models are created based on the adaptive model settings. You can view these settings through this action or by opening the adaptive model.

To view the settings:

1. Locate the model for which you want to view the model configuration settings.
2. In the Actions menu, select View Model Parameters to open the Adaptive Model Parameters dialog.
3. Inspect the settings used for creating models.

Upload responses

The Upload Responses wizard lets you train the model by uploading existing customer data representing previous behavior or sample data. The use of previous results lets Adaptive Decision Manager create models that are able to predict behavior.

ADM only considers positive and negative cases that correspond to the possible outcomes taken into account by the settings defined in the adaptive model. It is also possible to train models through activities.

To upload responses follow these steps:

1. Select File: Select the CSV file containing the input data for each case.
2. Select Outcome: Select the column that provides the outcome for each case.
3. Map Outcome: Map the outcome in the sample or historical data to the possible outcome defined in the adaptive model rule.

Related information

Open topic with navigation