Create an incident prediction model in Task Intelligence for ITSM

  • Release version: Yokohama
  • Updated January 30, 2025
  • 2 minutes to read
    • Summarize
    Summarized using AI
    This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete.

    Summary of Create an incident prediction model in Task Intelligence for ITSM

    Task Intelligence for ITSM enables ServiceNow customers to create and deploy incident prediction models that forecast key incident fields for new IT service incidents. These models help automate incident categorization by leveraging historical case data to predict incident details, improving efficiency and accuracy in incident management.

    Show full answer Show less

    Key Features

    • Customizable Prediction Parameters: Admins can define which fields the model predicts (output fields), which fields it uses for predictions (input fields), and set conditions to select training records.
    • Prediction Behavior Options: Choose how predictions are applied—auto-fill fields, provide recommendations, monitor in the background only, or turn off predictions.
    • Base System Models Included: Prebuilt similarity-based models are provided for predicting similar incidents, related open change requests, problems, and major incident recommendations. These models install automatically with the Task Intelligence for ITSM plugin and train on your instance data.
    • Model Monitoring and Editing: Performance results can be viewed in the Task Intelligence for ITSM Monitoring dashboard, allowing admins to refine and redeploy models. Models can also be configured to display predictions within the Service Operations Workspace.
    • Seamless Integration: The base models link to the Recommended Actions for ITSM configuration, requiring no additional rule setup by admins for enabling prediction-driven recommendations.

    How It Benefits ServiceNow Customers

    By using incident prediction models, customers can accelerate incident handling by automatically suggesting or filling incident fields based on learned patterns from past incidents. This reduces manual data entry, enhances consistency in incident categorization, and supports better decision-making through timely recommendations. The ability to customize and monitor models ensures continuous improvement and alignment with organizational needs.

    Next Steps

    To implement incident prediction, admins should:

    • Set up a new incident prediction model using the provided templates or edit the base system models to fit specific requirements.
    • Train the model with historical incident data and review test predictions to evaluate performance.
    • Configure prediction preferences and behaviors (auto-fill, recommend, monitor).
    • Deploy the model to start making predictions on new incident records.
    • Monitor model performance regularly via the Task Intelligence for ITSM Monitoring dashboard and adjust configurations as needed.

    Create and deploy solution-based incident categorization prediction models to predict incidents fields for new IT service incidents.

    With an incident field prediction model, you can choose what the model uses to predict information. If you're an admin, you can decide when you want it to make predictions, what you want it to predict, and what data to use for those predictions. You can select the following information:
    • Output fields: The fields that the model predicts
    • Input fields: The fields used to predict the output fields
    • Conditions that choose the set of records to train the model
    • The prediction behavior: auto-fill, recommend, or Monitor only (run in the background) or turn off predictions.

    After customizing your model, you can view the test results and deploy the model.

    The model uses previous case records to train. You can see how the model would have predicted fields for past cases, providing you with an estimate of how the model performs when deployed.

    Base system model

    Task Intelligence for ITSM comes with a base system which has following models based on similarity:
    • Similar Incidents: For predicting the similar incidents for incidents table.
    • Similar open Change Requests for Incident: For predicting the similar change requests for incident table.
    • Similar open Problems for Incident: For predicting the similar problems for incident table.
    • Major Incident Recommendation: For recommending similar active major incidents which the current incident can be linked to, and for recommending that you propose similar incidents as a major incident.

    When you install the Task Intelligence for ITSM plugin in your production instance, the model is installed and is trained on your data automatically. This model is auto-deployed. The model starts predicting data in the background and doesn’t impact the Incident form.

    The prediction data is then stored in the prediction tables. You can navigate to All > Task Intelligence for ITSM > Monitoring to view the performance results of this model. Based on these results, you can edit the model to show the predictions in Service Operations Workspace. You can configure the model to use the predictions to either auto-fill or give recommendations for the output fields on an incident form.

    To edit and redeploy the base system model, you can navigate to the Setup page. From the model list, select the required similarity model and edit the model. For more information on how to edit the model, see Edit an incident prediction model in Task Intelligence for ITSM.

    This model is linked with a base system rule in the Recommended Actions for ITSM configuration. An admin isn't required to go to the Recommended Actions for ITSM application to configure any rules for this model.

    To set up a new model using a template, see Set up your incident prediction model.