mathewshen's comments

On: Time-Series Anomaly Detection: A Decade Review

[mathewshen]

Very surprised that I can see this paper here and it deserved! I start fellow the work of Dr. Boniol since 2021(By the series2graph paper). The Series2Graph is an very good algorithm that works well in some complex situations. And his later works like New Trends in Time-Series Anomaly Detection, TSB-UAD, Theseus and k-Graph and so on are very insightful too.

[mathewshen → mathewshen]

If you want to see more algorithms/systems that are used in industry company like Twitter/Microsoft/Amazon/LinkedIn/IBM/..., you can see my note here(The source page is in Chinese, and I just translate it into English using Google Translate): https://datahonor-com.translate.goog/odyssey/aiops/tsad/pape...

[countzro → mathewshen]

I also liked the main idea of Series2Graph but found the implementation a bit complicated.

There is a similar algorithm with a simpler implementation in this paper: „GraphTS: Graph-represented time series for subsequence anomaly detection“ https://pmc.ncbi.nlm.nih.gov/articles/PMC10431630/

The approach is for univariate time series and I found it to perform well (with very minor tweaks).

[mathewshen → countzro]

Agree. And thanks for the recommendation, I'd like to read the paper of GraphTS.

On: Beer: Challenging Problems in Probability and Stat...

[mathewshen]

You can check the project's motivation here: https://datahonor-com.translate.goog/beer/blog/2024/04/15/ab...