Use case · Anomaly detection

Autonomous AI anomaly detection, with thresholds you can trust.

Drop your sensor, transaction, log, or network data. OctOpus rotates across forecast-residual, isolation, and autoencoder approaches — and validates the threshold on real holdout windows so you don't ship a detector that alerts on everything.

TL;DR. The hard part of anomaly detection isn't building the detector — it's setting the threshold. OctOpus picks the method per data shape (time-series → forecast-residual; tabular → isolation forest or autoencoder; sparse labels → PU learning) and validates the operating threshold on a holdout slice with realistic anomaly density.

What OctOpus detects well

Methods the agent rotates through

Data shapeMethodThreshold strategy
Time series, no labelsForecast (LightGBM lags · NeuralForecast · Chronos) → residual z-scoreQuantile of historical residuals on holdout window.
Tabular, no labelsIsolation forest, one-class SVM, autoencoder reconstruction errorQuantile-based, validated against synthetic injection if needed.
Few labelsPU learning · weakly-supervised GBMThreshold tuned on the labeled positives via PR curve.
Many labelsStandard supervised classification (escalates to classification)F-beta optimization on holdout.

What you get back

Detect anomalies free → See benchmarks vs traditional AutoML