Timeline for Combining time series anomaly measures
Current License: CC BY-SA 4.0
10 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 31, 2022 at 14:24 | answer | added | Stephan Kolassa | timeline score: 0 | |
| Jul 31, 2022 at 14:00 | comment | added | sinpalabras | Ok, so what if we assume that it is possible to label part of the data? | |
| Jul 30, 2022 at 12:50 | comment | added | Stephan Kolassa | The problem still is that if you don't have the ground truth for at least some of your data, it seems like a rather fruitless exercise. How would you know you are doing the right thing? You could "combine" your scores by labeling all data points as "anomalous", or none of them, or just pick one of your classifiers at random. How would you know any of these methods don't work? | |
| Jul 30, 2022 at 12:47 | comment | added | sinpalabras | Thanks for your response, I tried to add more info in the original post. | |
| Jul 30, 2022 at 12:46 | history | edited | sinpalabras | CC BY-SA 4.0 |
added 766 characters in body
|
| Jul 26, 2022 at 17:19 | comment | added | Stephan Kolassa | Hm. I would not try to train a classifier on "normal" data alone. I think if you gave more context, it might be easier to help you. | |
| Jul 26, 2022 at 16:11 | comment | added | sinpalabras | Hi. Part of the data can be seen as normal (not containing anomalies) and can be used for training/calibration/finding thesholds. But the whole problem is rather unsupervised/semi-supervised. | |
| Jul 24, 2022 at 19:20 | comment | added | Stephan Kolassa | Do you have a ground truth of data points explicitly labeled as anomalous? | |
| S Jul 24, 2022 at 18:22 | review | First questions | |||
| Jul 25, 2022 at 1:42 | |||||
| S Jul 24, 2022 at 18:22 | history | asked | sinpalabras | CC BY-SA 4.0 |