Predictive Intelligence-Regression Framework Issue
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
‎05-04-2023 07:15 AM - edited ‎05-05-2023 03:01 AM
Hi,I trained the Regression solution to predict the Resolve Time of an Incident using Short Description and linked it with the system using the before insert business rule, but I received an error message stating that "applyPredictionForSolution(gr, solution) is only applicable for classification solutions." while creating an Incident . Below is a screenshot of the business rule, solution statistics and error message. Also Looking for an explanation of how the Resolve Time is related to the ML solution's Point Estimate, Upper Bound, and Lower Bound.

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
‎05-12-2023 06:21 AM
Hi Meenakshi, have you tried the newer ML API to call your regression solution? The applyPredictionForSolution has been deprecated and may not work with regression.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
‎05-18-2023 03:35 AM
Hi @Lener Pacania1
Thank you for the reply.
-Tried with above ML Predictor() to call the regression solution but still facing the same error "applyPredictionForSolution(gr, solution) is only applicable for classification solutions."Is there any other changes to be made to call the regression solution.
-Also the resolve time is not getting populated when an incident is created. Is there any other configuration changes we have to do to reflect in the resolve time field of an incident.
-Also Looking for an detailed explanation of how the Resolve Time is related to the ML solution's Point Estimate, Upper Bound, and Lower Bound.
-How to increase the Range accuracy and reduce the SMAPE in the regression solution.