Specify a boosted ensemble
Boosting is more advanced than bagging because models are trained sequentially, with each model improving on the previous one, instead of all models learning in parallel. There are several R packages that implement this powerful algorithm, and tidymodels
has you covered. It provides a simple interface to generate boosted trees.
Your task in the following three steps is to create the initial specification for an ensemble of boosted trees that you will use in the following exercises.
This exercise is part of the course
Machine Learning with Tree-Based Models in R
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Specify the model class
boost_spec <-___()
boost_spec