I am trying to predict weekly sales using ARMA ARIMA models. I could not find a function for tuning the order(p,d,q) in statsmodels
. Currently R has a function forecast::auto.arima()
which will tune the (p,d,q) parameters.
How do I go about choosing the right order for my model? Are there any libraries available in python for this purpose?
Advertisement
Answer
You can implement a number of approaches:
ARIMAResults
includeaic
andbic
. By their definition, (see here and here), these criteria penalize for the number of parameters in the model. So you may use these numbers to compare the models. Also scipy hasoptimize.brute
which does grid search on the specified parameters space. So a workflow like this should work:def objfunc(order, exog, endog): from statsmodels.tsa.arima.model import ARIMA fit = ARIMA(endog, order, exog).fit() return fit.aic() from scipy.optimize import brute grid = (slice(1, 3, 1), slice(1, 3, 1), slice(1, 3, 1)) brute(objfunc, grid, args=(exog, endog), finish=None)
Make sure you call brute
with finish=None
.
You may obtain
pvalues
fromARIMAResults
. So a sort of step-forward algorithm is easy to implement where the degree of the model is increased across the dimension which obtains lowest p-value for the added parameter.Use
ARIMAResults.predict
to cross-validate alternative models. The best approach would be to keep the tail of the time series (say most recent 5% of data) out of sample, and use these points to obtain the test error of the fitted models.