Timeline for Raw data outperforms Z-score transformed data in SVM classification
Current License: CC BY-SA 3.0
18 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Dec 15, 2021 at 22:14 | history | edited | Sycorax♦ |
edited tags
|
|
| S Jun 16, 2016 at 9:31 | history | bounty ended | Shovalt | ||
| S Jun 16, 2016 at 9:31 | history | notice removed | Shovalt | ||
| Jun 16, 2016 at 9:30 | comment | added | Shovalt | @GeneralAbrial, thanks for your answer. You are correct, the question you mentioned does seems like a possible duplicate. On the other hand, I could imagine intuitively why 0-1 scaling can destroy results (a single outlier can do that), while z-score scaling doesn't seem so trivial to me. That's why I didn't search for problems with scaling in general. | |
| Jun 16, 2016 at 9:23 | history | edited | Shovalt | CC BY-SA 3.0 |
Added clarifications in response to comments
|
| Jun 15, 2016 at 19:36 | answer | added | caveman | timeline score: 0 | |
| Jun 10, 2016 at 21:18 | history | tweeted | twitter.com/StackStats/status/741379081321713664 | ||
| Jun 10, 2016 at 16:35 | history | edited | Sycorax♦ | CC BY-SA 3.0 |
edited body
|
| Jun 10, 2016 at 16:33 | answer | added | Sycorax♦ | timeline score: 7 | |
| Jun 10, 2016 at 16:33 | comment | added | Sycorax♦ | This question is a duplicate of the question asked here: stats.stackexchange.com/questions/172795/… but we can't close it because the bounty is open. | |
| Jun 10, 2016 at 16:05 | answer | added | Haitao Du | timeline score: 2 | |
| Jun 9, 2016 at 13:12 | comment | added | user83346 | see my answer below, hope it helps | |
| S Jun 9, 2016 at 6:55 | history | bounty started | Shovalt | ||
| S Jun 9, 2016 at 6:55 | history | notice added | Shovalt | Draw attention | |
| May 31, 2016 at 10:56 | comment | added | Shovalt | Yes, I mean different C and different gamma. It seems that because the orders of magnitude are different, I need to find the optimal parameters for each type of data (normalized and raw) or I may not get a separation at all. Perhaps I am wrong, but working with the same params definitely doesn't work. FYI - The default SVC params work ok with the Z-score data and not at all with the raw, which makes sense to me. | |
| May 31, 2016 at 9:52 | comment | added | user83346 | If you say that the parameters of the svm's are not identical, do you mean the in both cases you have different radius r for the rbf? And/or different C? Did you try with identical values? | |
| May 31, 2016 at 8:16 | review | First posts | |||
| May 31, 2016 at 8:33 | |||||
| May 31, 2016 at 8:10 | history | asked | Shovalt | CC BY-SA 3.0 |