Splunk Dev

Predict Volume using MLTK

rony121
Loves-to-Learn Lots

Hi All,

I am new to Machine Learning Toolkit. I have a use case to implement to predict volume of sales depending on days of weeks/ hourly/towards end or beginning of months and on special holidays days.  Apart from predicting the volume of sales, I would also like to generate thresholds as upper bound and lower bound and alert when crossing the upper bound or lower bound

Which of the ML algorithm is best suitable for this kind of use case?

Raw date:
A lookup storing the sales in every 30mins in last one year.

TimeSales
23/03/2021 01:30195
23/03/2021 02:00570
23/03/2021 02:303580
23/03/2021 03:001350
23/03/2021 03:30103
23/03/2021 04:00245
Labels (3)
0 Karma

srijondas
Explorer

Use percentiles/standard deviation to generate the thresholds and check how the predicted values compare to the upper/lower thresholds. it should be possible to do it within the ML query. 

0 Karma
Got questions? Get answers!

Join the Splunk Community Slack to learn, troubleshoot, and make connections with fellow Splunk practitioners in real time!

Meet up IRL or virtually!

Join Splunk User Groups to connect and learn in-person by region or remotely by topic or industry.

Get Updates on the Splunk Community!

Enterprise Security Watch Party: What’s New in 8.8 - Recap

Splunk Community HQ hosted a Splunk Enterprise Security Watch Party: What’s New In ES 8.8 last Thursday. I had ...

Move CrowdStrike FDR ingestion to Data Inputs with a guided migration

CrowdStrike Falcon Data Replicator data is essential for security investigations, detections, and response. It ...

Make Your Machine Data AI-Ready in Splunk

Every team is getting ready for AI agents.    Watch On-Demand   In this Tech Talk, Splunk platform specialists ...