Mike Tokic

Hey Matt and team, I was hoping you could remove the numeric check in the lag_vec() function. I'd like to use lag_vec() within tk_augment_lags() to create lag variables for things...

prevent very large forecasts which can create errors when writing to disk

Look into adversarial validation to help detect data drift and when to retrain/reselect models.

create grouped aggregations of target variable for bottoms up forecast

1

To help the model distinguish between different groups in the data. May only be applicable to global models.

adam and ets models from the smooth package can now be integrated into modeltime

Investigate the upside of leveraging data.table transformations to speed up data processing within the package. Could be helpful when forecasting large datasets (millions of rows). https://dtplyr.tidyverse.org/ https://www.business-science.io/code-tools/2021/04/13/dtplyr-datatable-dplyr-backend.html?utm_content=buffere2297&utm_medium=social&utm_source=linkedin.com&utm_campaign=buffer

need to adjust back testing process when running a yearly forecasts. Currently a year is the minimum smallest amount of training data when doing model refitting, which works for quarterly...

https://github.com/AlbertoAlmuinha/neuralprophet

automated text feature engineering with NLP