After you create an intelligent inspection job, anomalies in time series data fail to be identified. This topic describes the possible causes for this issue.
- Anomalies occurred before the intelligent inspection job is created.
Historical data is used only for model training. The algorithm model does not identify anomalies in historical data.
- The algorithm model has not consumed sufficient data after the intelligent inspection job is created.
The algorithm model must consume at least 200 data points before the model can identify anomalies.
- After you create the intelligent inspection job, the algorithm model consumes data before non-metric data is written to the source Logstore.
To resolve this issue, you can increase the value of the Data Latency parameter. For more information, see Use SQL statements to aggregate metrics for real-time inspection.
- The anomaly score that is generated by the algorithm model is less than or equal to 0.5.
The algorithm model identifies the anomalies whose scores are greater than 0.5 for data points.
If the issue persists after you troubleshoot the issue based on the preceding causes, submit a ticket.