Detecting Anomalies

  1. Go to a project detail page.
  2. Click Detect Anomalies.
  3. Browse for or drag and drop the CSV or JSON file that contains your data set in the Detect Anomalies box.
  4. Click Detect.

    The anomalies are represented in a list of columns that can be visualized.

  5. Select a column label to view the detected anomalies.
    Each visualization can be viewed by selecting a different column label from the list.
  6. If you want to view or use the generated anomalies JSON file, click Download JSON.

The estimated and actual values of each of the identified anomalies are rendered in a graph. You can use this difference to learn the severity of the anomaly.

If multiple anomalies occurred from various signals at specific time stamp, then the anomaly scores that ranks those signals for the identified anomaly are given. A graph of these anomalies over the given time period displays so that you can easily understand if there are specific signals that have high scores over time.