This message was deleted.
# neural-forecast
s
This message was deleted.
👍 2
c
we can definitely attest to a difference in ease of tuning, but the lift against xgboost is significant (at least in our domain) and persists across ~95% of all of our ~1k forecasting tasks
v
XGBoost is all about creating features. Could this be the issue?
c
we ran both with and without tsfresh features, same finding held up.
👍 1
v
Nice there is also new one for features could be interesting for team https://github.com/predict-idlab/tsflex
c
awesome, will give this a try 👍
v
Did DL win on global models (multi series) or univariate as well?
c
yah for clarity this is all for multioutput single series using exogenous variables
👍 1