LLM-Generated Feature Pools for Time Series Anomaly Detection
Quick summary
arXiv:2609.21801v1 Announce Type: new Abstract: We study how far a simple statistical pipeline can go on univariate time series anomaly detection under a strict selection protocol. The method extracts a small pool of statistics over sliding windows, scores each window with a transductive robust (MAD) model, and selects a feature subset per domain on a held-out tuning split. On TSB-AD-U it reaches $0.529$ per-series VUS-PR, above the best neural ($0.45$) and statistical ($0.44$) entries on the public leaderboard and within $0.06$ of the strongest pretrained foundation model, several of which us
Key takeaways
- arXiv:2609.21801v1 Announce Type: new Abstract: We study how far a simple statistical pipeline can go on univariate time series anomaly detection under a strict selection protocol.
- The method extracts a small pool of statistics over sliding windows, scores each window with a transductive robust (MAD) model, and selects a feature subset per domain on a held-out tuning split.
- On TSB-AD-U it reaches $0.529$ per-series VUS-PR, above the best neural ($0.45$) and statistical ($0.44$) entries on the public leaderboard and within $0.06$ of the strongest pretrained foundation model, several of which us
Why it matters
“LLM-Generated Feature Pools for Time Series Anomaly Detection” is a product decision that may change how people work with AI. Its value depends on task completion, correction effort and data handling—not simply the presence of a new feature.
Member comments