Skip to main content


         This documentation site is for previous versions. Visit our new documentation site for current releases.      
 

Troubleshooting an adaptive model with only one active predictor

Updated on August 29, 2021

Beginning with Pega Platform 8.4, Prediction Studio sends a notification when an adaptive model instance has access to only one active predictor. An adaptive model with only one active predictor might not provide accurate predictions. Improve model performance by identifying and addressing the root cause of the issue. The possible root causes include the low predictive performance of the model predictors, or the model continuing to collect a sufficient number of responses. The issue can also occur if you feed the historical data to the model instance in a certain order, for example, negative responses first, and then positive responses.

Notification text

Adaptive Model modelName Model only has 1 active predictor.

Recommended next steps

Identify and address the root cause of the issue by performing the following procedures:

Verify the number of registered responses

  1. In Prediction Studio, open the adaptive model by clicking the corresponding notification.
  2. On the Monitor tab, for the affected model instance, click Model report.
  3. Expand the Model details section, and then, in the Number of responses section, verify the number of responses that the model instance registered for each response type:
    • If each response type has less than 100 responses, wait until the model receives more responses.
    • If each response type has more than 100 responses, go to step 4 in Verify predictor performance

Verify predictor performance

  1. In Prediction Studio, open the adaptive model by clicking the corresponding notification.
  2. On the Monitor tab, for the affected model instance, click Model report.
  3. On the Predictors tab, verify the predictive performance score of the model predictors:
    • If all or most predictors have a predictive performance score below 52 Area Under the Curve (AUC), add predictors that potentially have a higher correlation with the outcome.

      For more information, see Adding a predictor to an adaptive model.

    • If all or most predictors have a predictive performance score above 52 AUC, go to Reset the model.

Reset the model 

Note: By resetting the model, you cause the model to start learning from the beginning based on new incoming responses. Consider resetting the model after verifying that the model instance received the learning data in a particular order, for example, by viewing the interaction history. For more information, see Monitoring interaction results.
  1. In the header of Dev Studio, click Configure > Decisioning > Model Management.
  2. On the Model Management landing page, click Adaptive.
  3. Select the adaptive model for which you received the notification by selecting the corresponding check box.
  4. Click Clear.
  • Previous topic Troubleshooting an adaptive model with no active predictors
  • Next topic Troubleshooting decision strategies by using interaction rules

Have a question? Get answers now.

Visit the Support Center to ask questions, engage in discussions, share ideas, and help others.

Did you find this content helpful?

Want to help us improve this content?

We'd prefer it if you saw us at our best.

Pega.com is not optimized for Internet Explorer. For the optimal experience, please use:

Close Deprecation Notice
Contact us