Which of the following is a disadvantage of boosting algorithms?Review LaterBoosting can lead to underfittingBoosting can be computationally expensiveBoosting requires a large number of hyperparametersBoosting is not suitable for imbalanced data

How does boosting handle class imbalance?Review LaterBoosting oversamples the majority class to balance the classes.Boosting assigns higher weights to misclassified instances to focus on the minority class.Boosting assigns higher weights to correctly classified instances to focus on the minority class.Boosting uses undersampling to balance the classes.

Which of the following is true about the Gradient Boosting trees?2 pointsIn each stage, introduce a new regression tree to compensate the shortcomings of existing modelWe can use gradient decent method for minimize the loss functionNeither A nor BBoth A and B

Question No. 4Marks : 1.00    Bagging speeds up model training by parallelizing computation, while boosting reduces overfitting by adding regularization           Bagging creates multiple datasets by sampling with replacement, while boosting adds models sequentially and adjusts their weights based on the error of the previous models

Which of the following is a hyperparameter in boosting algorithms?Review LaterLearning rateNumber of estimatorsMaximum depthSubsample size

Which ensemble learning technique is more suitable for reducing overfitting?Review LaterBaggingBoostingBoth bagging and boosting are equally effective.Neither bagging nor boosting can help reduce overfitting.