Testing and monitoring predictions

Evaluate the coverage and precision of your machine-learning (ML) solutions by testing them. Once deployed, track their performance over time. Improve predictions by using performance information to refine your solutions.

Testing solutions

After your ML solutions are trained, you can call on the Predictive Intelligence API to make a solution prediction. Use the API to test the following solutions:

• Test a classification solution prediction
• Test a similarity solution prediction

Monitoring predictions

For classification predictions, use the Prediction Results dashboard to track the coverage and precision of predictions over time.

To learn how, see Track classification prediction results over time.

Prediction troubleshooting

For troubleshooting common issues with solution predictions, see the Predictive Intelligence Common issues [KB781893] article in the Now Support Knowledge Base.

• Test a classification solution prediction
  Once your machine-learning (ML) solutions are trained, you can call on the Predictive Intelligence API to make a solution prediction. In this example procedure, we use the REST API Explorer to test a classification solution prediction for incident categorization.
• Test a similarity solution prediction
  Once your machine-learning (ML) solutions are trained, you can call on the Predictive Intelligence API to make a solution prediction. In this example procedure, we use the REST API Explorer application to test a similarity solution prediction for resolved incident recommendations.
• Track classification prediction results over time
  Use the Prediction Results dashboard to determine if classification solution predictions are improving over time. Identify solutions that need refining or retraining.
• Reviewing prediction errors with the Observability Dashboard
  The Observability Dashboard offers a unified view and actionable insights for errors detected in Predictive Intelligence. Use this dashboard to visualize logged errors and gain information on prediction reliability and potential problem areas.
• Predictive Intelligence Usage Analytics dashboard
  The Predictive Intelligence Usage Analytics dashboard is a central location to understand the effectiveness and overall value of all your Predictive Intelligence solutions. View metrics for model training successes and failures. Monitor prediction statistics including breakdowns by individual model.