[HN Gopher] Adventures in Imbalanced Learning and Class Weight
___________________________________________________________________
Adventures in Imbalanced Learning and Class Weight
Author : andersource
Score : 23 points
Date : 2025-05-08 13:41 UTC (2 days ago)
(HTM) web link (andersource.dev)
(TXT) w3m dump (andersource.dev)
| ipunchghosts wrote:
| I read the article and the take away is that class weights and
| stratified sampling did not help for the OPs problem.
| lamename wrote:
| Nice writeup. F1, balanced accuracy, etc. In truth it depends on
| your problem and what a practical "best" solution is, especially
| in imbalanced scenarios, but Matthews Correlation Coefficient
| (MCC) is probably the best comprehensive and balanced blind go-to
| metric, because it guarantees that more portions of the confusion
| matrix are good [0,1].
|
| I made a quick interactive, graphical exploration to demonstrate
| this in python [2].
|
| [0]:
| https://biodatamining.biomedcentral.com/articles/10.1186/s13...
|
| [1]:
| https://biodatamining.biomedcentral.com/articles/10.1186/s13...
|
| [2]: https://www.glidergrid.xyz/post-archive/understanding-the-
| ro...
___________________________________________________________________
(page generated 2025-05-10 23:00 UTC)