Exploring Anomalies

After you run the anomaly detection process, you can interactively explore the anomalies in your analysis, along with the key drivers.
To explore anomalies for an insight:
  1. Click Dashboards tab, the Dashboards tab.
  2. Click Dashboard Designer, in the bottom-left corner.
  3. On the Analyses dialog, click Options button, the Options button, next to an analysis and select Edit.
  4. On the analysis page, select an anomaly detection insight.
    Make sure that the detection process ran successfully and that the insight displays the identified anomalies and the last time the results were updated. For more information, see Configuring Anomaly Detection.
  5. Click Menu options button, the Menu options button, in the corner of the insight and select Explore anomalies.
  6. On the Insights page, expand the Controls bar at the top and configure the settings available for exploring anomalies.
    • Severity: The level of sensitivity for detecting anomalies.

      For example, you see more anomalies when the threshold is set to Low and above and fewer anomalies when the threshold is set to High and above. This sensitivity is determined based on standard deviations of the anomaly score generated by the machine learning algorithm.

    • Direction: The direction on the x-axis or y-axis that you want to identify as anomalous.

      The default option, [ALL], identifies all anomalous values, high and low. You can select Higher than expected or Lower than expected to identify only higher values or only lower values as anomalies.

    • Minimum delta - absolute value: The absolute threshold to identify anomalies. Any amount higher than the threshold value counts as an anomaly.
    • Minimum delta - percentage: The percentage threshold to identify anomalies. Any amount higher than the threshold value counts as an anomaly.
    • Sort by: The sort method applied to the results.

      These options are available:

      • Weighted anomaly score: The anomaly score multiplied by the logarithm of the absolute value of the difference between the actual value and the expected value. This score is always a positive number.
      • Anomaly score: The actual anomaly score assigned to this data point.
      • Weighted difference from expected value: The anomaly score multiplied by the difference between the actual value and the expected value. This is the default option.
      • Difference from expected value: The actual difference between the actual value and the expected value.
      • Actual value: The actual value with no formula applied.

    • Categories: One category setting is displayed for each category field that you added to the Categories field well. You can use the category settings to filter the data.

    A list of anomaly charts is displayed on the Insights page based on your configurations. Each category or dimension has a separate chart that uses the field name as the chart title.

  7. To display or hide the Number of anomalies chart that shows anomalies detected over time, click the Show anomalies by date or Hide anomalies by date option.
    Hover over a bar in the chart to view the number of anomalies for that point in time. Click one of the bars to display a chart that shows the values for the analyzed data metric before and after the anomaly.
  8. To see information about key drivers, look at the Contributors panel at the left of the page.

    At the top of the panel, you can see a summary that describes any changes in the data metrics.

    Under Top Contributors, you can see the results of the top contributor analysis for the specified time frame. Hover over the entries to see more details.

    To change the sort method applied to the results, select one of the options available under Sort by. You can select Absolute difference, Contribution percentage, Deviation from expected, or Percentage difference.

    Note: The Contributors panel is displayed only if the anomaly detection is configured to also analyze key drivers.
Parent topic: Configuring Anomaly Detection