Developing for Splunk Enterprise

Predict Volume using MLTK

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.

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 (4)
0 Karma


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
Did you miss .conf21 Virtual?

Good news! The event's keynotes and many of its breakout sessions are now available online, and still totally FREE!