https://github.com/nixtla logo
c

Cristian (Nixtla)

07/18/2023, 9:34 PM
Hi <!channel>, we are happy to announce that we added a full implementation of the classic DeepAR model (and its
auto
counterpart) from Amazon to the library! The main difference between DeepAR and the standard
LSTM
is the recursive Monte Carlo sampling to produce probabilistic forecasts. Give it a try and let us know how it works!
🥰 2
👍 3
nixtla 9
🙌 4
🔥 17
c

Chris Gervais

07/18/2023, 10:04 PM
this is on 1.6.1?
c

Cristian (Nixtla)

07/18/2023, 10:04 PM
yes!
c

Chris Gervais

07/18/2023, 10:05 PM
awesome 👍
s

Sapna Mishra

07/18/2023, 10:14 PM
This is amazing! Thanks!
m

Manuel

07/19/2023, 8:37 AM
@Cristian (Nixtla) Is there a summary page in the documentation that shows which algorithms support exogenous variables, static exogenous variables, etc.? Something like this: https://unit8co.github.io/darts/userguide/covariates.html#global-forecasting-models-gfms
c

Cristian (Nixtla)

07/19/2023, 2:24 PM
Not right now, but thanks for the suggestion, we will definitely add it to this page: https://nixtla.github.io/neuralforecast/examples/models_intro.html
🙌 1