Decision trees
A detailed look at decision trees, how they work, how they are made, and are combined to make random forests.
Decision trees are a commonly used method for classification problems, though they may also be used for regression. They are called trees as they organise sets of smaller decisions in a hierarchical structure which physically resembles a tree, with branches and leaves (or nodes).
In this video we look at decision trees in detail, including:
- What are decision trees and what do they do?
- What is the process for creating a decision tree?
- Evaluating the decisions made by each node using Gini impurity
- Methods to avoid overfitting e.g. pruning
- Creating multiple decision trees, known as random forests.
