# About details of Multi-Metric Anomaly Detection **URL:** \ **Category:** Kibana\ **Tags:** elastic-stack-machine-learning\ **Created:** [January 4, 2022, 7:31am UTC](https://discuss.elastic.co/t/about-details-of-multi-metric-anomaly-detection/293413 "2022-01-04T07:31:40Z")\ **Posts on this page:** 8\ **Page:** 1
**Author:** ![Furkan](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/furkan/32/78301_2.png) [@Furkan](https://discuss.elastic.co/u/Furkan)\ **Post date:** [January 4, 2022, 7:31am UTC](https://discuss.elastic.co/t/about-details-of-multi-metric-anomaly-detection/293413/1 "2022-01-04T07:31:40Z")
Hi, In the multi-metric job in anomaly detection, do the metrics affect each other to find the anomalies as multivariate anomaly detection or is the main point of multi-metric job creating a job for different metrics in same time-interval (instead of creating multiple single-metric job for same time interval, creating multi-metric job for the metrics) ? I saw a topics and tutorials on that, but these are a little bit old, I want to re-ask. Thanks... ---
**Author:** ![richcollier](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/richcollier/32/115035_2.png) [@richcollier](https://discuss.elastic.co/u/richcollier)\ **Post date:** [January 4, 2022, 9:12pm UTC](https://discuss.elastic.co/t/about-details-of-multi-metric-anomaly-detection/293413/2 "2022-01-04T21:12:03Z")
It is not multi-variate in the way that you might be thinking (a confluence of multiple variables affecting a specific feature of interest) - rather it is a parallel analysis of multiple features simultaneously (for scale/efficiency). You can either create multiple `detectors` (i.e. `max(this)` and `sum(that)`, etc.) or "split" the analysis along a categorical feature via `partition`/`by` fields (`count partition=error_code` or `max(responsetime) by service`). ---
**Author:** ![Furkan](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/furkan/32/78301_2.png) [@Furkan](https://discuss.elastic.co/u/Furkan)\ **Post date:** [January 5, 2022, 7:59am UTC](https://discuss.elastic.co/t/about-details-of-multi-metric-anomaly-detection/293413/3 "2022-01-05T07:59:09Z")
@richcollier Thanks for your response and located the topic to the right category, In addition, is there a way of checking anomaly detection conditions are occurred (as one or more switch), can this be adjusted in Kibana interface or Anomaly Detection API? Thanks again for your response... ---
**Author:** ![richcollier](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/richcollier/32/115035_2.png) [@richcollier](https://discuss.elastic.co/u/richcollier)\ **Post date:** [January 5, 2022, 11:54am UTC](https://discuss.elastic.co/t/about-details-of-multi-metric-anomaly-detection/293413/4 "2022-01-05T11:54:29Z")
Hi @Furkan I don't understand your question and what you mean by "as one or more switch". Can you ask in a different way? ---
**Author:** ![Furkan](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/furkan/32/78301_2.png) [@Furkan](https://discuss.elastic.co/u/Furkan)\ **Post date:** [January 5, 2022, 1:12pm UTC](https://discuss.elastic.co/t/about-details-of-multi-metric-anomaly-detection/293413/5 "2022-01-05T13:12:36Z")
@richcollier I was asking, Can we build or automate to the anomaly detection process to condition-based instead of time-based detection? Thanks... ---
**Author:** ![richcollier](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/richcollier/32/115035_2.png) [@richcollier](https://discuss.elastic.co/u/richcollier)\ **Post date:** [January 5, 2022, 8:13pm UTC](https://discuss.elastic.co/t/about-details-of-multi-metric-anomaly-detection/293413/6 "2022-01-05T20:13:25Z")
If your data has no element of time but is purely attribute-based, you could consider using [outlier detection](https://www.elastic.co/guide/en/machine-learning/current/dfa-outlier-detection.html). ---
**Author:** ![Furkan](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/furkan/32/78301_2.png) [@Furkan](https://discuss.elastic.co/u/Furkan)\ **Post date:** [January 6, 2022, 6:06am UTC](https://discuss.elastic.co/t/about-details-of-multi-metric-anomaly-detection/293413/7 "2022-01-06T06:06:43Z")
Thanks for your responses... ---
**Author:** ![system](https://us1.discourse-cdn.com/elastic/original/3X/1/a/1ac57faf039f6b580b3f104ef42a2a89e41014de.png) [@system](https://discuss.elastic.co/u/system)\ **Post date:** [February 3, 2022, 6:07am UTC](https://discuss.elastic.co/t/about-details-of-multi-metric-anomaly-detection/293413/8 "2022-02-03T06:07:28Z")
This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.