Timeline for OOB Score vs test set accuray Random Forest
Current License: CC BY-SA 3.0
13 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jan 3, 2021 at 21:46 | answer | added | Pandian Le | timeline score: 1 | |
| Nov 30, 2020 at 8:04 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Jul 30, 2020 at 14:02 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Mar 27, 2020 at 21:01 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Nov 20, 2019 at 18:02 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Jul 25, 2019 at 0:30 | comment | added | EngrStudent | There should be purpose in decisions. Are the classes balanced? I hear you talking about time series, but I don't see how you are handling lags. Can you talk about the shape of your data? If I had 30k rows and 8 features, I would trade it in for 29k rows and 8000 features. That is data more "fit" for a random forest. I would use Boruta to chew that 8k features to 40 features that would do some real good. | |
| Jul 19, 2019 at 20:31 | comment | added | Ceph | @EngrStudent 2000 trees might be overkill in the sense of wasted time/computation, but adding too many trees doesn't cause overfitting under RF. | |
| Jul 19, 2019 at 18:09 | comment | added | EngrStudent | It is relatively hard to overfit with a random forest. Max depth is a little low, min samples is a little high, and max features candidated is crazy low. Could you move that up to the late 80's? What does the convergence look like that drives 2000 trees? For many cases 200 is overkill and 80 to 100 will do. Eight features is not a lot of features for 30k samples. You could augment with a hundred first lags (or leads depending on ordering) to get a better model. I don't see you talking about how 3 measurements ago informs next prediction. | |
| Jul 19, 2019 at 18:01 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Mar 17, 2019 at 20:01 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Sep 13, 2017 at 12:38 | answer | added | PhilippPro | timeline score: 1 | |
| Aug 31, 2017 at 15:09 | review | First posts | |||
| Aug 31, 2017 at 15:25 | |||||
| Aug 31, 2017 at 15:06 | history | asked | Simon | CC BY-SA 3.0 |