modeltime.gluonts
modeltime.gluonts copied to clipboard
DeepAR: Student t vs. Negative Binomial
Hello Matt,
I'm very new to your great package and have a question with regard to the distribution used by deepAR-model. As far I understood it correctly, it uses Student t-distribution by default. For my data, I'm interested in negative binomial distribution. Based on the basic example:
model_fit_deepar <- deep_ar( id = "id", freq = "M", prediction_length = 24, lookback_length = 48, epochs = 5 ) %>% set_engine("gluonts_deepar") %>% fit(value ~ ., training(m750_splits))
could you explain how I can adjust it to negative binomial distribution.
Many Thanks in advance!