Related Data Science Links
Learn Decision Trees Data Science Tutorial, validate concepts with Decision Trees Data Science MCQ Questions, and prepare interviews through Decision Trees Data Science Interview Questions and Answers.
Decision Trees Q&A
1What is a decision tree?
Answer: Rule-based model splitting data recursively by feature thresholds.
2Why are trees interpretable?
Answer: Predictions follow transparent if-then paths.
3Split criteria for classification?
Answer: Gini impurity or entropy/information gain.
4Split criteria for regression?
Answer: Variance reduction or MSE reduction.
5What is overfitting in trees?
Answer: Deep trees memorize noise and generalize poorly.
6How control complexity?
Answer: Limit max depth, min samples split/leaf, and prune.
7What is pruning?
Answer: Removing weak branches to improve generalization.
8Can trees handle nonlinear relationships?
Answer: Yes, naturally through hierarchical splits.
9Do trees need feature scaling?
Answer: Usually no, unlike distance-based models.
10How handle missing values?
Answer: Some implementations support surrogate/learned split handling.
11Main limitation?
Answer: Single trees can be unstable to small data changes.
12One-line summary?
Answer: Decision trees are interpretable but often improved by ensembles.