SPOTは、一変量時系列におけるストリーミング[[外れ値検出]]である。 ## Papers - [[2017__KDD__Anomaly Detection in Streams with Extreme Value Theory]] - [Anomaly Detection in Streams with Extreme Value Theoryを読んだ - yasuhisa's blog](https://www.yasuhisay.info/entry/2017/11/14/073000) ## Libraries - [GitHub - limjcst/ads-evt: Anomaly Detection in Streams with Extreme Value Theory](https://github.com/limjcst/ads-evt) - [[2022__KDD__Causal Inference-Based Root Cause Analysis for Online Service Systems with Intervention Recognition|CIRCA]]で使用されている [CIRCA/evt.py at 03ec82a1a7534900bcc30d5ae09ceb8ba8beb984 · NetManAIOps/CIRCA · GitHub](https://github.com/NetManAIOps/CIRCA/blob/03ec82a1a7534900bcc30d5ae09ceb8ba8beb984/circa/alg/evt.py) - [GitHub - Amossys-team/SPOT: SPOT algorithm implementation (with variants)](https://github.com/Amossys-team/SPOT) - [GitHub - cbhua/model-pot: Algorithms about Peaks-over-Threshold, including POT, Stream POT, and DSPOT.](https://github.com/cbhua/model-pot) - [GitHub - asiffer/libspot: Born to flag outliers](https://github.com/asiffer/libspot)