In this chapter, we looked at very important machine learning methods for creating an ensemble model by stacking in the framework. In stacking, we used base models (learners) to create predicted probabilities that were used on input features to another model (a super learner) to make our final predictions. Indeed, the stacked method showed an improvement over the individual base model. We performed all of this using mlr (machine learn), which is a powerful tool for any R machine learning practitioner.

Up next, we're going to delve into the world of unsupervised learning, where we're not trying to predict a label or quantitative outcome, but rather to understand patterns in the observations or features.