---
sourceDocument: Yokohama IT Operations Management
sourceDocumentLink: https://servicenow-prod.fluidtopics.net/r/yokohama/it-operations-management

 Release :

    - yokohama

ft:locale :

    - en-US

ft:publication_title :

    - Yokohama IT Operations Management

ft:clusterId :

    - itom

bundleId :

    - itom

workflow :

    - Technology


---

# Create an anomaly test rule

# Create an anomaly test rule {#ariaid-title1}

* Release version: Yokohama
* 
* Updated January 30, 2025
* 
* ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 minutes to read

To use the anomaly model testing, create an anomaly test rule in which you specify up
to 20 metric series to test anomaly detection for. Run the anomaly test, and after it
completes, use the provided URL to open the Insights Explorer which is pre-loaded with the
model testing results.

## Before you begin

Role required: evt_mgmt_user

## Procedure

1. Navigate to AllEvent ManagementAnomaly DetectionAnomaly Model Testing.
2. Select an existing anomaly test rule to edit and run again, or click New and fill out the Anomaly Test Rules form.  
   {#anomaly-model-testing__table_hlv_3j2_tdb__entry__2}

   | Field | Description |
   |-|-|
   | Name | Name for the model test rule. |
   | Applies to | The table from which to select CI/metric pairs for the model test rule. The table used is Metric To CI Mapping \[sa_metric_map\]. |
   | Rule | Filter conditions to specify pairs of CIs/metrics for the anomaly model testing. If the rule yields more than 20 pairs of CIs/metrics, then the list is truncated to 20. |
   | Start date/End data | The time period for which to apply the anomaly detection testing. The time period must be within the past 7 days. |
   | Status | Status of the test, automatically updated by the system during a test run. Status is initially Scheduled and eventually changes to Complete. |
   | URL | URL to the Insights Explorer in which the anomaly model test results are pre-loaded. |
   | Notes | Logging summary, automatically updated by the system with details of each test run of the anomaly test rule. |
   [ ]

   {#anomaly-model-testing__table_hlv_3j2_tdb}
3. Click Run Anomaly Test.  
   During the test run, the Status, URL, and Notes fields are automatically updated to reflect the progression of the job.
4. After Status changes to Complete, click the URL link to open the Insights Explorer to see the results of the test.

## Result

The bounds and the chart for the anomaly model test, appear in faint colors in Insights Explorer. Also, the upper and lower bounds that are calculated by the test, use a line pattern that is different than line pattern used for actual anomaly detection results. These differences let you distinguish between actual anomaly detection and anomaly model test results, if both are selected in the chart settings.

## What to do next

* Modify the date range for the test or choose different time series, and click Run Anomaly Test again to continue and fine-tune the model.
* Click the Chart Settings icon for a chart to toggle the display of statistics and aggregations on the chart. Select Show Bounds and Show Anomaly Scores in the Anomaly Test Statistics and in the Anomaly Statistics sections, to display test results next to actual anomaly detection results.  
  Note:  
  Anomaly Model Testing results might be very similar to actual anomaly detection results. If you configure the chart to display both at the same time, as you move the mouse over the chart, it might be difficult to identify points of differences.
* When you are satisfied with the anomaly test results, enable anomaly detection in the production environment, for the metrics and CIs specified in the test. See [Choose and configure metrics to monitor](https://servicenow-prod.fluidtopics.net/TeSckDnQjs0TeuDpJai2Og "Metric Intelligence uses data sources that can be monitoring hundreds of metrics for all CIs. Choose for each data source type which details are important for which CIs, and then activate or deactivate the respective monitor type to control the amount of data that is being processed.") for more details.
{#anomaly-model-testing__ul_qpr_wyj_tdb}
**Related tasks**   

* [View metric values in the Insights Explorer](https://servicenow-prod.fluidtopics.net/rkMOjVXRik8MRa3YErou2Q "Metric Intelligence calculates statistics for CI metric data. Insights Explorer displays these metric values as metric charts for the CIs in the CMDB. Insights Explorer lets you overlap any metrics for any CIs in a single chart to create a multi-layered view of metric values across a time range.")

*[\>]: and then