https://github.com/nixtla logo
m

mike

11/17/2022, 10:35 PM
Currently trying to migrate from
fable
to statsforecast in our production environment. However, I’m running into an issue with replication. Is it possible to
boxcox
transform prior to the forecasting step and back transform to produce the forecast mean rather than median? I’ve tried using the
scipy
python package, but it’s producing lower predictions than the R implementation. Any ideas / thoughts? Examples: ETS ->
fable::ETS(fabletools::box_cox(qty + 1, lambda = 0.3), opt_crit = "mae")
ARIMA ->
fable::ARIMA((fabletools::box_cox(qty + 1, lambda = 0.4)) ~ PDQ(period = 13), stepwise = TRUE)
THETA ->
THETA(fabletools::box_cox(qty + 1, lambda = 0.1) ~ season(method = "additive"))
Looks like it’s implemented in the
AutoARIMA
class, but still getting fairly low predictions:
AutoARIMA(stepwise=True,season_length=13,blambda=0.4,biasadj=0.4)
m

Max (Nixtla)

11/17/2022, 10:50 PM
Hi @mike, thanks for the question. We will have a look and come back to you with an answer.
m

mike

11/17/2022, 11:06 PM
@Max (Nixtla) - Thank you!!