# Measure for uncertainty of the Anomaly Detection algorihtm

**URL:** <https://discuss.elastic.co/t/measure-for-uncertainty-of-the-anomaly-detection-algorihtm/238662>\
**Category:** Kibana\
**Tags:** elastic-stack-machine-learning\
**Created:** [June 25, 2020, 12:01pm UTC](https://discuss.elastic.co/t/measure-for-uncertainty-of-the-anomaly-detection-algorihtm/238662 "2020-06-25T12:01:39Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![JorritvdLaan](https://avatars.discourse-cdn.com/v4/letter/j/ee59a6/32.png) [@JorritvdLaan](https://discuss.elastic.co/u/JorritvdLaan)\
**Post date:** [June 25, 2020, 12:01pm UTC](https://discuss.elastic.co/t/measure-for-uncertainty-of-the-anomaly-detection-algorihtm/238662/1 "2020-06-25T12:01:40Z")

</div>

Hello,

We are trying to find anomalies in people's daily power usage using Elastic's Anomaly Detection.

Of course, in order to detect a day-night cylce, the algorithm first needs some data before it can recognize patterns.  
However, the time it takes before such a cycle is picked up can differ a lot.  
Sometimes the model needs only 2 days worth of data, and sometimes it does not happen at all. See the images below.

 ![Even_pattern](https://us1.discourse-cdn.com/elastic/original/3X/2/8/28d01afe83f250f6410e7e5727ab55b70e367309.png) ![Slightly_oneven_pattern](https://us1.discourse-cdn.com/elastic/original/3X/9/6/96bca984c585dce1bdba5aa28bf29fa4a08d4fc8.png) ![Uneven_Pattern](https://us1.discourse-cdn.com/elastic/original/3X/4/1/4181e05ca1e3014e02b61420551d07eaa85e275f.png)

In the second image in the middle a clear point can be seen at which the model "understands" the data. Is there a way to automatically detect this change in behaviour?

I was thinking about analysing the rate of change in the model bounds, but have not found a way to retrieve these when there are no anomalies. I also noticed that the forecast-functionality does something similar when it checks whether enough data is provided. Is it possible to run such a check without the forecasting?

Thanks in advance,

Jorrit van der Laan

---

<div class="post-metadata">

**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:** [June 29, 2020, 4:08pm UTC](https://discuss.elastic.co/t/measure-for-uncertainty-of-the-anomaly-detection-algorihtm/238662/2 "2020-06-29T16:08:06Z")

</div>

There will be an upcoming feature in which significant model changes will be published to ML's Annotations: [https://github.com/elastic/elasticsearch/issues/55781](https://github.com/elastic/elasticsearch/issues/55781)

---

<div class="post-metadata">

**Author:** ![JorritvdLaan](https://avatars.discourse-cdn.com/v4/letter/j/ee59a6/32.png) [@JorritvdLaan](https://discuss.elastic.co/u/JorritvdLaan)\
**Post date:** [June 30, 2020, 9:19am UTC](https://discuss.elastic.co/t/measure-for-uncertainty-of-the-anomaly-detection-algorihtm/238662/3 "2020-06-30T09:19:41Z")

</div>

Looks interesting! Do you know when this upcoming feature would be released?

---

<div class="post-metadata">

**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:** [June 30, 2020, 2:37pm UTC](https://discuss.elastic.co/t/measure-for-uncertainty-of-the-anomaly-detection-algorihtm/238662/4 "2020-06-30T14:37:08Z")

</div>

We cannot commit exactly, but possibly v7.9.

---

<div class="post-metadata">

**Author:** ![system](https://us1.discourse-cdn.com/elastic/original/3X/1/a/1ac57faf039f6b580b3f104ef42a2a89e41014de.png) [@system](https://discuss.elastic.co/u/system)\
**Post date:** [July 28, 2020, 2:37pm UTC](https://discuss.elastic.co/t/measure-for-uncertainty-of-the-anomaly-detection-algorihtm/238662/5 "2020-07-28T14:37:17Z")

</div>

This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.