Decision Trees & Random Forest

Definition

A decision tree splits data with if/else questions; a random forest averages many trees for better accuracy.

Trees are interpretable and forests are strong on tabular data.

Diagram

Flowchart

Example: Random forest

from sklearn.ensemble import RandomForestClassifier
X=[[0,0],[1,1],[0,1],[1,0]]; y=[0,1,0,1]
print(RandomForestClassifier(random_state=0).fit(X,y).predict([[1,1]]))

Output: [1]

Key points

• Splits use Gini or entropy
• Single trees overfit
• Forests reduce variance

Interview questions

More Machine Learning topics