decision tree

Decision Tree

A machine learning model that makes predictions by asking a sequence of yes/no questions about input features, routing each observation down the tree to a prediction.

When you'd see it: As a building block inside Random Forests and gradient boosting, and standalone when interpretability is required. A single decision tree can be visualized and explained to non-technical stakeholders — the entire decision logic is visible as a flowchart.

Why it matters: Decision trees are the most interpretable of the commonly-used ML models. They show exactly the decision logic the model uses, which matters in regulated industries (credit, healthcare, insurance) where model decisions need to be explainable to regulators or customers.

Common mistakes: Using a single decision tree for production predictions where accuracy matters. Trees memorize training data (high variance) and underperform on new data. Ensembles (Random Forest, gradient boosting) almost always outperform a single tree for prediction accuracy.

Related Random Forest, gradient boosting, overfitting, confusion matrix