btw we’re starting to get some pretty conclusive r...
# neural-forecastc
Chris Gervais
11/08/2022, 11:18 AMbtw we’re starting to get some pretty conclusive results re: neuralforecast performance as benchmarked against xgboost, catboost, lightgbm etc. @Valeriy not sure if you’ve had a chance to wrap up your analysis but seems pretty clear at this point the conclusion from https://arxiv.org/abs/2106.03253 is bogus
👍 2
Chris Gervais
11/08/2022, 11:23 AMwe 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
Valeriy
11/08/2022, 11:23 AMXGBoost is all about creating features. Could this be the issue?
c
Chris Gervais
11/08/2022, 11:25 AMwe ran both with and without tsfresh features, same finding held up.
👍 1
v
Valeriy
11/08/2022, 11:26 AMNice there is also new one for features could be interesting for team https://github.com/predict-idlab/tsflex
c
Chris Gervais
11/08/2022, 11:26 AMawesome, will give this a try 👍
v
Valeriy
11/08/2022, 11:29 AMDid DL win on global models (multi series) or univariate as well?
c
Chris Gervais
11/08/2022, 11:46 AMyah for clarity this is all for multioutput single series using exogenous variables
👍 1