View Task Intelligence prediction history

  • Release version: Xanadu
  • Updated August 8, 2024
  • 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 View Task Intelligence Prediction History

    This guide provides instructions on accessing and understanding the historical prediction data from the Task Intelligence Predictor Result table, which is crucial for monitoring model performance in ServiceNow's Customer Service module.

    Show full answer Show less

    Key Features

    • The Predictor Result table logs each prediction result, detailing the predicted language, predicted values, actual values, and prediction confidence.
    • Access to the History module is restricted to users with the roles of Task Intelligence admin and Customer Service manager.
    • Categorization feedback captures discrepancies between predicted and actual case values when a case is closed, enhancing the training of categorization models.
    • Email categorization solutions utilize data from the Email table, while case categorization solutions draw from the Case table or its extensions.
    • Final input and output values, along with predicted confidence percentages, are recorded to assess prediction accuracy.

    Key Outcomes

    By reviewing the Predictor Result table, users can effectively evaluate the performance of their categorization models and make informed decisions to improve customer service operations. Additionally, understanding how to prevent duplicate entries in email sentiment analyses helps maintain accurate data in the system.

    View details about historical predictions in the Predictor Result [ml_predictor_results] table.

    The Predictor Result table includes entries for each prediction result, including the predicted language, predicted and actual values, and prediction confidence. You can use the data in this table to monitor model performance.
    Note:
    Records are created in the Predictor Result table regardless of the model prediction behavior. This includes the Testing behavior that does not add prediction values to the case.

    Viewing prediction data

    Navigate to All > Task Intelligence for Customer Service > History to view the Predictor Result list.

    Users with the following roles can access the History module:
    • Task Intelligence admin [sn_csm_ml_task.ti_admin]
    • Customer Service manager [sn_customerservice_manager]
    Categorization feedback captures values when the status of a case changes to Closed. It captures these values if:
    • Case categorization is active.
    • The predicted field value is different from the case field value.

    Categorization feedback works for record categorization solutions and for solutions with and without attachments. Email categorization solutions are trained using data from the Email [sys_email] table. Case categorization solutions are trained using data from the Case [sn_customerservice_case] table or from tables that extend the Case table. Interaction categorization solutions are trained using data from the Interaction [interaction] table.

    Categorization feedback is triggered by a flow.
    • When email information is used for prediction, the final input values remain empty.
    • When attachment information is used for prediction, the attachment sys_ids are not included in the final input values.
    Categorization feedback stores the following values in the Predictor Result table:
    • Predicted Output Value Name
    • Predicted Input Value Names
    • Predicted Output Value
    • Predicted Input Values
    • Final Input Value
    • Final Output Value
    • Predicted Confidence (percentage)
    If the values for a case have been predicted using an email categorization solution:
    • The Final Input Value remains blank because it is not expected that the agent will modify the values of the email, such as subject and body.
    • When the case is closed, the final value in the Predicted Output Value is stored in the Final Output Value.
    If the values for a case or interaction have been predicted using a record categorization solution:
    • The values from the fields defined in Predicted Input Value Names are stored in Final Input Value.
    • When the case is closed, the final value in the Predicted Output Value is stored in the Final Output Value.

    Email sentiment replies

    Duplicate entries can be posted in the Predictor Result table for email sentiment replies. To prevent these duplicate entries, deactivate the Predict Sentiment for Cases inbound email action. For more information, see Inbound email actions.