Timeline for Can overfitting be a good thing in some cases?
Current License: CC BY-SA 4.0
7 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Feb 15, 2023 at 21:39 | comment | added | dimitriy | In your example, where does the function that turns the current assignment submission status into the probability of future dropout come from? | |
| Feb 15, 2023 at 20:39 | answer | added | Zmelgar K1R3D2 | timeline score: 0 | |
| Oct 19, 2018 at 13:32 | comment | added | kjetil b halvorsen♦ | See this post for an interesting viewpoint | |
| Oct 19, 2018 at 13:11 | answer | added | cherub | timeline score: 4 | |
| Oct 19, 2018 at 12:57 | comment | added | Björn | You mean you only want to have a kind of efficient way of memorizing the data (in that case overfitting is indeed good)? Or do you actually want to predict new data from the same users (only a certain type of overfitting is good - this may e.g. change your cross-validation strategy)? | |
| Oct 19, 2018 at 10:57 | answer | added | Sangathamilan Ravichandran | timeline score: 3 | |
| Oct 19, 2018 at 10:41 | history | asked | renakre | CC BY-SA 4.0 |