AirQo African Air Quality Prediction Challenge
$3 000 USD
Completed (over 1 year ago)
Prediction
1029 joined
514 active
Start
Mar 15, 24
Close
Jun 16, 24
Reveal
Jun 16, 24
'%3e%3cg id='b'%3e%3cpath id='a' d='M0-8v8h4z' transform='rotate(18 0 -8)'/%3e%3cuse xlink:href='%23a' transform='scale(-1 1)'/%3e%3c/g%3e%3cuse xlink:href='%23b' transform='rotate(72)'/%3e%3cuse xlink:href='%23b' transform='rotate(144)'/%3e%3cuse xlink:href='%23b' transform='rotate(216)'/%3e%3cuse xlink:href='%23b' transform='rotate(288)'/%3e%3c/g%3e%3c/svg%3e){kind=small}
Can we use SMOTE ?
Notebooks · 25 May 2024, 07:24 · 4
Hi! I hope the competition is going well for all of you!
I have a small problem: when performing cross-validation, I see that the score for one of my groups is considerably lower than the scores for the other groups. To fix this issue, I thought about using SMOTE to generate more data from that specific group, but I’m not sure if it is allowed in this competition. Could you please assist me? Also, if there are any other ways to deal with the problem, please let me know!
SMOTE is used for classification problems.
Sorry, my bad! I was thinking too much about the idea of over-sampling my minority group.
Variations of SMOTE can be used for regression problems as well. There are several versions, and you have to determine what you are trying to accomplish by using them. For regression, you can use SMOTER or SMOGN.
The key thing is "SMOTE" specifically is for classification problems.