dotnet / dotnet/machinelearning-modelbuilder

Difference in predicted values in Evaluate-Tab and App (with same Feature-values!)

Open
#3,057 0 comments 0 reactions 0 assignees View on GitHub
GS Tutorial
Dominant language
Dockerfile
Stars
285
Forks
66
PR merge metrics
No merged PRs in 30d

Description

Hi

**System Information (please complete the following information):**
- Model Builder or CLI Version: latest installed 12.07.2025
- Visual Studio Version (if applicable): 17.14.8 Win

**Describe the bug**
Evaluate Tab with "Try your Model". The Feature-values were insertes automatically after the succesful Model-train.
LightGbmRegression RSquared: 0,8022. I receive a predicted Result of: 3,39, but when I use the Model in my App with the provided Code Snippet in "Consume"-Tab I receive a predicted value of 1,70595. The Feature-values i inserted are the same.
**Why do I have such a difference?**
I use SQL Express based database with apprx 500k records?

Image
Image
Image

Thank you and best regards
Christian

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.