Timeline for How to choose a classifier after cross-validation?
Current License: CC BY-SA 3.0
10 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Sep 20, 2016 at 17:39 | comment | added | nmc | Sure! Just trying to mention something else to think about :) | |
| Sep 16, 2016 at 8:37 | vote | accept | Armon Safai | ||
| Sep 14, 2016 at 19:09 | answer | added | Javierfdr | timeline score: 16 | |
| Sep 13, 2016 at 18:26 | comment | added | Armon Safai | @NathanMcCoy well assuming we pick accuracy, we would choose the classifier with the highest test accuracy? | |
| S Sep 13, 2016 at 13:40 | history | suggested | tuomastik | CC BY-SA 3.0 |
Changed title to match the question
|
| Sep 13, 2016 at 9:45 | comment | added | nmc | I think this question depends a lot on the metric used to determine "best approach". Quantifiably many people use accuracy, but depending on the data set, other metrics can be used such as a Harmonic mean like F1-Score. So metric choice can be equally important. | |
| Sep 13, 2016 at 7:48 | review | Suggested edits | |||
| S Sep 13, 2016 at 13:40 | |||||
| Sep 13, 2016 at 7:42 | answer | added | tuomastik | timeline score: 8 | |
| Sep 13, 2016 at 7:15 | answer | added | Hima Varsha | timeline score: 1 | |
| Sep 13, 2016 at 3:23 | history | asked | Armon Safai | CC BY-SA 3.0 |