-
It could be good to be able to use `reg_td()` with user-defined calendar. Currently, the trading-days regressors and the covariance structure are built inside Java, however they could be directly prov…
AQLT updated
2 months ago
-
In MESMER-M we estimate the parameters of the AR1 process to generate local temporally correlated variability. In principle, this is similar as in MESMER, except that we want AR parameters for each mo…
-
Hi,
Is there a way to pass a specific seasonal ARMA order to x13_arima_analysis rather than it examining the "maxorder" tuple for model identification.
Lets say, I want to pass the following SARIMA …
-
# Modeltime Ecosystem Roadmap
The __`modeltime` project roadmap__ tracks the overall development of the Modeltime Ecosystem of forecasting packages. Modeltime is a cutting-edge ecosystem for forec…
-
Hello,
I'm building a time series model, for forecasting Sales, based on the history since 2019.
My model uses SKForecast with XGBRegressor.
I want to forecast 75 days.
My target is SALES.
I…
-
@AlbertoAlmuinha Is it mandatory that the seasonal parameters be known beforehand for the `sarima_reg` or will the algorithm take what you give and adjust?
-
Investigate and implement `smooth` package. What makes immediate sense are:
- [ ] ADAM: Augmented Dynamic Adaptive Model https://forecasting.svetunkov.ru/en/2021/01/13/the-creation-of-adam-next-ste…