# Unsupervised Real-Time Anomaly Detection for Streaming Data

**URL:** https://discourse.numenta.org/t/unsupervised-real-time-anomaly-detection-for-streaming-data/3062
**Category:** Related Papers
**Created:** [November 16, 2017, 10:27am UTC](https://discourse.numenta.org/t/unsupervised-real-time-anomaly-detection-for-streaming-data/3062 "2017-11-16T10:27:15Z")
**Posts on this page:** 4
**Page:** 1

<div class="post-metadata">

### Author: ![Meylina](https://avatars.discourse-cdn.com/v4/letter/m/67e7ee/32.png) [@Meylina](https://discourse.numenta.org/u/Meylina)
#### Post date: [November 16, 2017, 10:27am UTC](https://discourse.numenta.org/t/unsupervised-real-time-anomaly-detection-for-streaming-data/3062/1 "2017-11-16T10:27:15Z")

</div>

Hey

I read the paper (and the supplementary material) and I was wondering if you had made some progress concerning the extension of HTM for a large number of data streams inputs. I am interesting to try, but I am afraid of the complexity of the training and inference.

---

<div class="post-metadata">

### Author: ![rhyolight](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/rhyolight/32/3922_2.png) [@rhyolight](https://discourse.numenta.org/u/rhyolight)
#### Post date: [November 16, 2017, 1:56pm UTC](https://discourse.numenta.org/t/unsupervised-real-time-anomaly-detection-for-streaming-data/3062/2 "2017-11-16T13:56:18Z")

</div>

A post was merged into an existing topic: [Real-Time Anomaly Detection for Streaming Analytics](https://discourse.numenta.org/t/real-time-anomaly-detection-for-streaming-analytics/1049)

---

<div class="post-metadata">

### Author: ![rhyolight](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/rhyolight/32/3922_2.png) [@rhyolight](https://discourse.numenta.org/u/rhyolight)
#### Post date: [November 16, 2017, 1:56pm UTC](https://discourse.numenta.org/t/unsupervised-real-time-anomaly-detection-for-streaming-data/3062/3 "2017-11-16T13:56:18Z")

</div>



---

<div class="post-metadata">

### Author: ![subutai](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/subutai/32/106_2.png) [@subutai](https://discourse.numenta.org/u/subutai)
#### Post date: [November 21, 2017, 2:53am UTC](https://discourse.numenta.org/t/unsupervised-real-time-anomaly-detection-for-streaming-data/3062/4 "2017-11-21T02:53:46Z")

</div>

Hi @Meylina - do you mean the section S4? I have tried it on a couple of datasets but not extensively (in part because we don’t have good datasets). Please let us know if you try it! In practical deployments we surprisingly found that the simple approach of just modeling each stream independently and then triggering an anomaly if any of them detected an anomaly worked reasonably well.