Hey, I'm using X-pack for Anomaly Detection.Is there any way to alter the conditions/rules in my ML job for which the anomaly is detected in my data? For example, i want anomalies to be detected only for zero/null values in my data. i also want anomalies to be detected if no value is input to my ML job
So, can we modify the rules to detect anomalies if there is no input data to the ML job for a given amount of time?
You don't need a custom rule for that. A simple detection configuration of
low_count will suffice. If the index you're interested in keeping track of suddenly gets lower input volume than it should, then you'll get an anomaly: