Knowledge MaxxingDecision tree
A decision tree predicts an outcome by asking a sequence of yes/no questions about feature values, branching until it reaches a final prediction.
Prerequisite: Classification
What matters
Because each prediction can be traced through a readable sequence of questions, decision trees are among the most directly interpretable model types, though a single tree can overfit easily.
Example
A decision tree predicting loan approval might first split on income, then within each branch split further on credit history, ending in a final approve or deny prediction.
Common misconception
A single decision tree is not usually the most accurate option available; it is often combined into an ensemble like a random forest for better performance.
Recall question
Why is a single decision tree's prediction easy to trace and explain?