Skip to content

Enhance model training process explanation #190

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
PrakshaaleJain wants to merge 4 commits into
base: master
Choose a base branch
from
Open

Enhance model training process explanation #190

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
1a43eb1
Enhance model training process explanation
PrakshaaleJain Aug 18, 2026
fbd15c8
Fix formatting in model training process description
alexeygrigorev Aug 18, 2026
85ebf29
Add explanation of feature importance differences
PrakshaaleJain Aug 20, 2026
1103454
Merge branch 'alexeygrigorev:master' into master
PrakshaaleJain Aug 20, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion theory.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -730,7 +730,7 @@ Also you can add random noise column to your data (with normal distribution), ca

**Are there any differences between continuous and discrete variables when it comes to feature importance of gradient boosting models? 🚀**

Answer here
Yes. Gradient boosting models heavily bias default feature importance metrics toward continuous variables because their wide range of unique values provides far more candidate split thresholds to reduce impurity compared to low-cardinality discrete variables. Additionally, one-hot encoding discrete features fragments their importance across multiple columns, while continuous features keep their entire signal concentrated in one.

<br/>

Expand Down