Anomaly detection types
Kloudfuse provides four Anomaly detection algorithms that overlay a probabilistic band on the metric, and display the expected behavior of a series based on past values.
- basic
-
Implements the Rolling Quantile algorithm.
Sampling interval: 1m, 2m, 3m, 5m, 10m, 15m, 30m, 1h, and 2h.
Numeric parameter: has the possible values of 1, 2, or 3.
- agile
-
Implements the SARIMA algorithm.
Numeric parameter: has the possible values of 1, 2, or 3.
- robust
-
Implements the Seasonal decompose algorithm.
Sampling interval: 1m, 2m, 3m, 5m, 10m, 15m, 30m, 1h, and 2h.
Numeric parameter: has the possible values of 1, 2, or 3.
- agile-robust
-
Implements the Prophet algorithm.
Sampling interval: hourly, daily, or weekly. Numeric parameter: has the possible values of 1, 2, or 3.
