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

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
25/100
Issue type
Bug
Clarity
Needs clarification
Activity status
Stale
Tech stack
sql

Research direction

Start by reproducing the prediction in the Evaluate-Tab’s “Try your Model” flow and in the generated Consume-Tab application, using the same feature values and model. Compare the model inputs and prediction paths, including the SQL Express data source, and establish whether both paths produce the same result or document the cause of the discrepancy.

Written by the indexing model from the issue text.

Description

GS Tutorial

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

Dominant language
Dockerfile
Stars
285
Forks
66
PR merge metrics
No merged PRs in 30d

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from dotnet/machinelearning-modelbuilder

All issues in dotnet/machinelearning-modelbuilder

Similar issues

More Databases issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.