Timeline for Handling categorical and ordinal data with highly imbalanced classes
Current License: CC BY-SA 3.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Mar 1, 2018 at 16:30 | vote | accept | thanasissdr | ||
| Feb 28, 2018 at 3:57 | answer | added | user20160 | timeline score: 2 | |
| Feb 28, 2018 at 1:36 | comment | added | Matthew Drury | That is not highly imbalanced. Highly imbalanced is a fraction of a percent. You need to fit a probabalistic model and tune the decision threshold. | |
| Feb 28, 2018 at 0:36 | comment | added | thanasissdr | @user20160 No, it's not aware of this, but in any case all the levels of every categorical feature are numbers, i.e. label encoding has been used. For the specific case of the random forest implementation, I haven't used one-hot encoding at all. | |
| Feb 28, 2018 at 0:22 | comment | added | user20160 | Are you using a random forest implementation that is explicitly aware of nominal/categorical variables? I ask because some implementations are not, and require some kind of numerical encoding (and one-hot may not perform well in these cases). | |
| Feb 27, 2018 at 23:14 | history | asked | thanasissdr | CC BY-SA 3.0 |