0
$\begingroup$

I am working on a case study to predict # of calls for next 30 days.

The data is at 30 minutes interval and start from 7 am to 23:30 PM (So 34 observations in a day).

I have two questions:

What would be the frequency ?

Which Machine Learning algorithm would be the best to predict next 30 days?

I tried LSTM, however it takes much longer just to complete 25 epochs.

$\endgroup$
0
$\begingroup$

You almost certainly have : there will be pattern within days, but weekdays will very likely also differ from weekends. So your frequencies will be both 34 (the length of intra-daily cycles) and 7*34=238 (the length of intra-weekly cycles). You may also have other periodicities, like monthly or yearly ones, but these will likely be the dominant ones.

The tag wiki contains pointers to useful forecasting algorithms and implementations in R (nothing in Python that I am aware of, sorry).

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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