Advanced Modeling Ensemble Methods: Bagging & Random Forests
About
Learn what ensemble methods are, how to fit and evaluate bagged decision trees and random forests, and how to compare their performance, benefits, limitations, and underlying rationale.
Learning Objectives
You will be able to:
- Define ensemble models and when to use them.
- Describe how and why decision trees can be improved using bagging and random forests.
- Fit and evaluate bagged decision trees and random forests.
- Understand how to calculate out-of-bag error.
- Explain how to extract the most important predictors in a random forest model.
Content
| Topic | Skills |
|---|---|
| Slides | - Conceptual overview of bootstrapping, bagging and random forests |
| Ensemble Methods: Bagging & Random Forests | - Walkthrough of ensemble learning, bootstrap sampling, and building a Bagging Classifier and a Random Forest Classifier model using scikit-learn. |
Prerequisites
- Construct individual decision trees.
- Describe how CART models are built.
- Differentiate between classification and regression problems.
- Understand the bias-variance tradeoff.
References
📖 Reference Materials
Important note
Please ignore the _layouts folder and the config.yml file in the root of this repo. They are needed to make sure the repo renders well; please don’t change them or delete them and your repo will work fine :)