Anomoly Detection Refresh

Q&A
,
1

Hi there,

I have recently been playing around with the Anomaly detection in Quicksight. The feature works great! However I’m wondering does the anomaly update automatically or is this something I have to run every time I want to discover an anomaly.

For example I have an anomaly set up in my dashboard to see when there is an anaomaly in the number of accounts created in a day. Will this now keep run again when there is another similar anomaly?

Also is it possible to notify people when an anomaly is detected?

Thanks,

Joe

2

You can configure the schedule for running the anomaly detection Adding an ML insight to detect outliers and key drivers - Amazon QuickSight

And you can also setup alert referring to here Anomaly detection alerting on previous periods - #3 by Yuval.Shiboli It will send an email to the user who configure this alert. But you cannot configure it sending to others.

3

Thank you,

Just to clarify, will the alert only trigger when there is a new anomaly? Or will it continue to alert this same anomaly?

Thanks,

4

can send new only or the old ones depends on how you configure.

There is an option “Set alert past period to receive notification email with anomalies from past several time periods” allow you to send alert for anomalies in the past period. If you don’t choose this, it will only show new anomaly

5

Hi @JSharman

It’s been a while since we last heard from you. If you have any further questions, please let us know how we can assist you.

If we don’t hear back within the next 3 business days, we’ll proceed with close/archive this topic.

Thank you!

6
  1. How does “Set alert past period to receive notification email with anomalies from past several time periods” work?
  2. I have setup anomaly detection to run on my SPICE dataset having enough data points on an HOURLY basis. Now the data which I get in dashboard is visists of my application every hour. So how does the schedule work , lets say every hour I can datapoints, it might be possible due to some lag in refresh 2-3 new data points come up so will the anomaly detection run for these 2-3 new data points and check if they breach threshold and then Alert me?
  3. In the above scenario if I setup Set Past Alerts as lets say so with every run will it check and give anomalies report in previous 9 runs as well because here I sometimes see that all values are not reported and the forecasted values also change
  4. Also if lets say the data which I am getting is aggregated on minute level in QUicksight and I setup anomlay runs at HOURLY (which is the minimum granularity available) then after every hour there are lot of new data points so it was giving very vague results, so does the algorithnm work for this case?