Facing an issue while creation of new incident for classification framework PI

Community Alums
Not applicable

Hi, Facing an issue while creating a new incident for a classification framework in predictive intelligence.How to sort this error message and why it occurs when we use a classification framework.

Thanks in advance.

1 ACCEPTED SOLUTION

Community Alums
Not applicable

Hi @Community Alums ,

Specify the records used to train a classification solution, what fields trigger a prediction, and how often you want to retrain your solution.

Please refer to this doc : https://docs.servicenow.com/bundle/tokyo-now-intelligence/page/administer/predictive-intelligence/task/create-solution-definition.html

 

View solution in original post

2 REPLIES 2

Community Alums
Not applicable

Hi @Community Alums ,

Specify the records used to train a classification solution, what fields trigger a prediction, and how often you want to retrain your solution.

Please refer to this doc : https://docs.servicenow.com/bundle/tokyo-now-intelligence/page/administer/predictive-intelligence/task/create-solution-definition.html

 

Community Alums
Not applicable

We tried out the solution but again we faced the same error message(apply prediction solution(gr solution) is only applicable for classification solution) while we trained a classification solution for populating the category field value based on a short description in the incident table but the predicted values are perfectly shown in the predictor results(ml_predictor_results) table but not in the real-time.
We've attached the Solution statistics snap. Can you tell the detailed information about precision, recall and coverage. 


Thanks in Advance.