Timeline for Is it possible to get confusion matrices from AUC?
Current License: CC BY-SA 3.0
7 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Dec 23, 2014 at 17:51 | vote | accept | Aleksandro M Granda | ||
| Dec 23, 2014 at 17:50 | vote | accept | Aleksandro M Granda | ||
| Dec 23, 2014 at 17:50 | |||||
| Dec 23, 2014 at 16:33 | comment | added | Marc Claesen | For cost-sensitive stuff you might want to read "Basic Principles of ROC Analysis" by Metz and the discussion about iso-performance lines in "An introduction to ROC analysis" by Fawcett. | |
| Dec 23, 2014 at 15:27 | comment | added | Aleksandro M Granda | Thanks for your answer! I understand that I need ROC curve shape to approximate exactly. I have number of instances per class and initial ROC curve, and I want to know is there any reason to improve the model (→ AUC) to reach a specific profit (sum of confusion matrix elements with weights). I have an idea to "inflate" the ROC curve, but it does not sounds good. Any ideas in this case? | |
| Dec 23, 2014 at 14:48 | history | edited | Marc Claesen | CC BY-SA 3.0 |
added figure of the curves
|
| Dec 23, 2014 at 14:42 | history | edited | Marc Claesen | CC BY-SA 3.0 |
edited body
|
| Dec 23, 2014 at 14:35 | history | answered | Marc Claesen | CC BY-SA 3.0 |