Algorithms · Foundational · Beginner

Decision Tree

A model that splits data by feature thresholds into a tree of if-then rules ending in a prediction.

What Decision Tree is

Decision trees are readable: the path from root to leaf is a literal explanation of the prediction, which makes them popular in regulated settings.

How it works

At each node the algorithm picks the split that best separates the target, measured by Gini impurity, entropy or variance reduction, and stops on depth or purity criteria. Pruning removes branches that do not generalise.

Why it matters

They are the building block of the ensembles that dominate tabular machine learning, and the clearest teaching example of how a model partitions feature space.

Common uses

→Rule extraction for policy
→Risk segmentation
→Base learners in ensembles

Strengths

✓Human-readable
✓No scaling required
✓Handles mixed data types

Watch for

✓Single trees overfit easily
✓Unstable to small data changes

Continue exploring

Ensemble Learning Gradient Boosting Explainable AI