Simple auto-regressive model to predict a time series

KCH Workflows
1

- Simple means just raw data: no seasonality correction, stationarity assumption - Auto means usage of past of the same time series for prediction. No other exogenous time series/data used. - Regressive refers to the model: either a linear or a polynomial regression

This is a companion discussion topic for the original entry at https://kni.me/w/9SsXq6DBqEsW8q-5
2

I’m wondering why the dataset was duplicated by concatenating here? Thank you!

3

Hi,
I don’t understand the output of the workflow where you have

  • Cluster
  • Prediction
    The prediction seems to be always done on a month for which you actually have sales isn’t it?
    On my side I’d like to project a sales forecast on the 3 next month (for which you abviously have no data).
    Is it possible?
    Any idea of how to perform this?
4

Hi there, i m not sure if this the right channel but i try :slight_smile:

I try to create Time Series Analysis with Components, this is a workflow described in blog.
But i have problem zu execute the node Decompose Signal. Is there any tricks that i need to know?
Thanks a lot!
Marija