Models Used in finnts

Univariate vs Multivariate Models

Global vs Local Models

Ensemble Models

Ensemble models are trained on predictions made by individual models. For example, a “glmnet-ensemble” model takes forecasts made by each individual model and feeds them as training data into a glmnet model. They also contain features related to date and forecasting horizon.

Deep Learning Models

The package contains multiple deep learning models that initially come from a python package called gluonts, which is developed by Amazon. They are called into R through a package called reticulate, which let’s python code run within R. In order to make these models run within R, you will need to install the proper python libraries, check out modeltime.gluonts to learn more about how to install everything properly.

Leveraging the Tidymodels Framework

Most of the models within the package are built on a fantastic time series library called modeltime, which was built on top tidymodels. Tidymodels is a fantastic series of packages that help in feature engineering (recipes), hyperparameter tuning (tune), model training (parsnip), and back testing (resample). Big shout out to the modeltime and tidymodels teams for being the shoulders this package stands on!