You want to combine the interpretability of a Decision Tree with the flexibility of KNN. Which pipeline design best achieves this?

Question

Answer

Use a Decision Tree for initial rule-based triage, then route uncertain cases (near the decision boundary) to KNN for refined local classification

Answer

Train both on separate random halves of the data and average their predictions

Answer

Use KNN's output as a feature for the Decision Tree

Answer

Replace the Decision Tree's leaf predictions with KNN predictions computed over the full dataset

Crowdly