Hello Splunk team and community,
I am working with the Splunk Machine Learning (ML) toolkit to detect anomalies in Oracle logs. Particularly, I have logs in Splunk that
contains both error and unerrored data, Is there any way where i need to detect anomalous in the logs says if there are suddenly some
50 errors received instead of normal by analyzing the history
If anyone has any ideas, tips, or guidance, I will be very grateful!
Thanks
Uma
Lots of people are going to recommend the out of the box anomaly detection in the MLTK to solve this.. While they are not wrong, this will lead to LOTS of Type 1 and Type 2 errors.
Check out my answer here on how to build out an anomaly detection framework in SPL