Why use nested cross-validation?

Question: Why is nested cross-validation used during model selection? A) To train the final model without validation data B) To remove the need for hyperparameter tuning C) To make the training set larger than the test set D) To estimate generalization performance while avoiding optimistic bias from hyperparameter tuning Correct: D Explanation: Nested cross-validation separates hyperparameter selection from final performance estimation. The inner loop tunes the model, while the outer loop estimates how well the selected model generalizes to unseen data. Topic: advanced ML / cross-validation / model selection