# Detect anomalies with ELK stack **URL:** \ **Category:** Elasticsearch\ **Created:** [October 22, 2018, 4:01pm UTC](https://discuss.elastic.co/t/detect-anomalies-with-elk-stack/153443 "2018-10-22T16:01:09Z")\ **Posts on this page:** 3\ **Page:** 1
**Author:** ![nita](https://avatars.discourse-cdn.com/v4/letter/n/bbe5ce/32.png) [@nita](https://discuss.elastic.co/u/nita)\ **Post date:** [October 22, 2018, 4:01pm UTC](https://discuss.elastic.co/t/detect-anomalies-with-elk-stack/153443/1 "2018-10-22T16:01:09Z")
Hello, I would like to use the ELK stack to manage and analyse logs but I'm totally new to it so I would be glad if you could give me some tips. I'd like to know if it is possible to detect anomalies using the ELK stack, I was thinking about something like filtering all the logs that have the "timetaken" value bigger than the 99th percentile but I'm stuck here, because Elasticsearch doesn’t permit subqueries. Is there any other way to do something like that? Or could you give me any other idea on how to use Elasticsearch for my purpose? Thanks in advance for your replies! ---
**Author:** ![Mark\_Harwood](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/mark_harwood/32/10538_2.png) [@Mark\_Harwood](https://discuss.elastic.co/u/Mark_Harwood)\ **Post date:** [October 22, 2018, 4:10pm UTC](https://discuss.elastic.co/t/detect-anomalies-with-elk-stack/153443/2 "2018-10-22T16:10:13Z")
The [machine learning](https://www.elastic.co/products/stack/machine-learning) feature set should be of interest. ---
**Author:** ![system](https://us1.discourse-cdn.com/elastic/original/3X/1/a/1ac57faf039f6b580b3f104ef42a2a89e41014de.png) [@system](https://discuss.elastic.co/u/system)\ **Post date:** [November 19, 2018, 4:10pm UTC](https://discuss.elastic.co/t/detect-anomalies-with-elk-stack/153443/3 "2018-11-19T16:10:17Z")
This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.