News for hackers. Stuff that matters.
Re:Dive into Time-Series Anomaly Detection: A Decade Review by ramon156 on Monday January 06, 2025 @08:05AM (#42610226)
I needed a TS anomaly detection for my internship because we needed to track when a machine/server was doing poorly or had unplanned downtime. I expected Microsoft's C# library to be able to do this, but my god, it's a mess. If someone has the time and will to implement a proper library then that would ve awesome.
Re:Dive into Time-Series Anomaly Detection: A Decade Review by neonsunset on Monday January 06, 2025 @08:16AM (#42610302)
Anomaly detection in time-series data is not a concern of the standard library of all things. Nor is it a concern of "base abstractions" shipped as extensions (think ILogger).
Re:Dive into Time-Series Anomaly Detection: A Decade Review by Phurist on Monday January 06, 2025 @12:02PM (#42612384)
If only life was as simple as calling .isAnomaly() on anything
Re:Dive into Time-Series Anomaly Detection: A Decade Review by neonsunset on Monday January 06, 2025 @01:32PM (#42613598)
Hardcoded to return 'false' of course. Because nothing ever happens!
Re:Dive into Time-Series Anomaly Detection: A Decade Review by sam_bristow on Tuesday January 07, 2025 @02:13AM (#42620130)
Just advertise it as guaranteed 0% false positive detections and you're good-to-go!
Re:Dive into Time-Series Anomaly Detection: A Decade Review by mr_toad on Tuesday January 07, 2025 @11:57AM (#42624569)
What you’re probably after is called statistical process control. There are Python libraries like pyspc, but the theory is simple enough that you could write your own pretty easily.