0
$\begingroup$

I would like to know if there are any methods to forecast multiple time series that are related ? I heard of LSTM but of what I can see it's more to forecast one time series and not several at the same time but I'm not sure. Any ideas are welcome, thanks :)

Improve this question
$\endgroup$

1 Answer 1

Reset to default
3
$\begingroup$

You could use vector autoregressive models to do this, please see the following resource: 11.2 Vector Autoregressive models VAR(p) models

This model is used for multivariate time series, and works by using each variable as a previous lag of itself as well as other variables.

In this regard, you could choose to model the multiple time series using statsmodels as per this example: statsmodels: Vector Autoregressions tsa.vector_ar

Improve this answer
$\endgroup$
1
  • $\begingroup$ Thanks and sorry for the late reply but I'm definitely going to give it a try $\endgroup$
    – Pierre21
    Commented Jan 9 at 9:35

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.