AI Layer
›4. Anomaly Detection
4. Anomaly Detection
A model that learns what normal looks like, per token, per session.
How it works
A trained model learns each token's normal spread, depth, and volume signature by session, then flags statistical deviations that fixed thresholds would miss.
What it catches
- Thin-hour manipulation
- Spoofed depth
- Coordinated wash activity
On This Page