Skip to main content
Determines whether the most recent point in a series is anomalous, using prior points as context. This endpoint is fully compatible with the Azure Anomaly Detector API. Ideal for real-time streaming detection where new points arrive one at a time. Both /anomalydetector/v1.0/timeseries/last/detect and /anomalydetector/v1.1/timeseries/last/detect are supported.
​
array
required
Array of data points. The last point is evaluated; prior points provide context. Minimum 12 points, maximum 8640 points. Timestamps must be sorted ascending with no duplicates.
​
string
default:"none"
Time interval between points. One of: yearly, monthly, weekly, daily, hourly, minutely, secondly, microsecond, none.
​
integer
default:1
Multiplier for granularity.
​
integer
default:0
Seasonality period. Set to 0 for auto-detection.
​
number
Maximum fraction of points that can be flagged as anomalies. Must be between 0 and 0.5 (exclusive).
​
integer
default:95
Detection sensitivity (0-99). Higher values flag more anomalies.
​
boolean
Whether the last point is anomalous.
​
boolean
Whether the last point is a negative anomaly.
​
boolean
Whether the last point is a positive anomaly.
​
integer
Detected seasonality period.
​
number
The model’s predicted value for the last point.
​
number
Upper margin for the last point.
​
number
Lower margin for the last point.
​
integer
Recommended context window size for future requests. Calculated as period * 4 + 1, or max(29, series_length) if no period is detected.
​
number
Severity score from 0.0 to 1.0.