Timeline for Why doesn't Mahout logistic regression give a good AUC when the model is tested on training data?
Current License: CC BY-SA 3.0
7 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| S Apr 4, 2016 at 13:23 | history | suggested | C8H10N4O2 | CC BY-SA 3.0 |
extraneous preface
|
| Apr 4, 2016 at 13:13 | review | Suggested edits | |||
| S Apr 4, 2016 at 13:23 | |||||
| Jan 20, 2015 at 13:05 | vote | accept | Emre Sevinç | ||
| Jan 19, 2015 at 9:48 | comment | added | Scortchi♦ | Haven't checked your code but note that there's no general reason to suppose the area under a receiver operating characteristic curve for a given model to be high, even calculated on the training set - why should all models be good? AUC values below 0.5 are possible, though unusual when the model's of even the slightest value, as it's log likelihood that's maximized in fitting rather than AUC. | |
| Jan 19, 2015 at 9:41 | answer | added | rapaio | timeline score: 2 | |
| Jan 19, 2015 at 9:13 | review | First posts | |||
| Jan 19, 2015 at 9:29 | |||||
| Jan 19, 2015 at 9:10 | history | asked | Emre Sevinç | CC BY-SA 3.0 |