Ensemble Modeling Interview Questions and Answers

Table of Content

• How is the Decision Tree constructed?
• What are the properties of Decision Trees?
• How does Decision Tree regression output work?
• What is the use of Decision Tree regression?
• To do the decision tree in R we will use which library?
• This Decision Tree is called _________?(which decision tree)
• Bootstrap aggregation is known for___________?
• In boosting technique what does the base_estimator parameter do?
• Which one is not in the Ensemble Techniques algorithm?
• Bagging comes under which _________ method?
• Which of the following are features of Random Forest?
• In boosting technique what does the n_estimator parameter do?
• Choose the wrong statement for ensemble technique?
• Which of the following ensemble techniques doesn’t use learning Rate as one of its hyper parameters?
• What is the importance of using the learning rate to get optimum output in boosting technique? Which of the following is true about choosing the learning rate?
• In random forest which hyper parameters are used for increasing the model's speed? Which of the following is the true statement?
• In a random forest, which hyper parameters are used for increasing the predictive power? Which of the following is a true statement?
• Ensemble technique can be used for both Regression and Classification Tasks?

• How is the Decision Tree constructed?

  • a) Entropy.
  • b) Information Gain.
  • c) Gini Impurity.
  • d) All the above.

  Answer - d) All the above

• What are the properties of Decision Trees?

  • a) Low Bias and high variance.
  • b) Low bias and low variance.
  • c) High bias and high variance.
  • d) High bias and low variance.

  Answer - a) Low Bias and high variance

• How does Decision Tree regression output work?

  • a) Mean and median.
  • b) Majority voting.
  • c) All the above.
  • d) None of this.

  Answer - a) Mean and median

• What is the use of Decision Tree regression?

  • a) Entropy.
  • b) Information Gain.
  • c) Mean squared error.
  • d) All the above.

  Answer - d) All the above

• To do the decision tree in R we will use which library?

  • a) e1071.
  • b) C5.0.
  • c) dist.
  • d) scale.

  Answer - b) C5.0

• This Decision Tree is called _________?(which decision tree)

  • a) Greedy.
  • b) Lazy Learner.
  • c) Market Basket.
  • d) Boosting.

  Answer - a) Greedy

• Bootstrap aggregation is known for___________?

  • a) Combines multiple weak learners into a single strong learner.
  • b) Sequential method.
  • c) Row sampling with replacement.
  • d) All the above.

  Answer - c) Row sampling with replacement

• In boosting technique what does the base_estimator parameter do?

  • a) Weak learner used to train the model.
  • b) Weak learners to train iteratively.
  • c) Contributes to the weights of weak learners.
  • d) All the above.

  Answer - a) Weak learner used to train the model

• Which one is not in the Ensemble Techniques algorithm?

  • a) Random forest.
  • b) Ad boost.
  • c) GBM.
  • d) Decision Tree

  Answer - d) Decision Tree

• Bagging comes under which _________ method?

  • a) Sequential methods.
  • b) Parallel method.
  • c) Line method.
  • d) Dot method.

  Answer - b) Parallel method

• Which of the following are features of Random Forest?

  • a) Reduce the variance.
  • b) Handle Over-Fitting.
  • c) It can also have internally imputation technique.
  • d) All of the above.

  Answer - d) All of the above

• In boosting technique what does the n_estimator parameter do?

  • a) Weak learner used to train the model.
  • b) Weak learners to train iteratively.
  • c) Contributes to the weights of weak learners.
  • d) All the above.

  Answer - b) Weak learners to train iteratively

• Choose the wrong statement for ensemble technique?

  • a) Based on the voting we can choose final classification prediction.
  • b) Based on the mean and median we can choose final regression prediction.
  • c) Avoid over–fitting.
  • d) Greedy algorithm is also known as ensemble technique.

  Answer - d) Greedy algorithm is also known as ensemble technique

• Which of the following ensemble techniques doesn’t use learning Rate as one of its hyper parameters?

  • a) Gradient Boosting
  • b) XGBMs
  • c) AdaBoost
  • d) Random Forest

  Answer - d) Random Forest

• What is the importance of using the learning rate to get optimum output in boosting technique? Which of the following is true about choosing the learning rate?

  • a) Learning rate should be as high as possible.
  • b) Learning Rate should be as low as possible.
  • c) Learning Rate should be low but it should not be very low.
  • d) Learning rate should be high but it should not be very high.

  Answer - c) Learning Rate should be low but it should not be very low

• In random forest which hyper parameters are used for increasing the model's speed? Which of the following is the true statement?

  Statement 1: n_jobs, random_state, oob_score(obb sampling)
  Statement 2: n_estimators, max_features, min_sample_leaf

  • a) Statement 1 is true and statement 2 is false.
  • b) Statement 1 is False and statement 2 is true.
  • c) Both Statement (1 & 2) is wrong.
  • d) Both Statement (1 & 2) is true.

  Answer - a) Statement 1 is true and statement 2 is false

• In a random forest, which hyperparameters are used for increasing the predictive power? Which of the following is a true statement?

  Statement 1: n_jobs, random_state, oob_score(obb sampling)
  Statement 2: n_estimators, max_features, min_sample_leaf

  • a) Statement 1 is true and statement 2 is false.
  • b) Statement 1 is False and statement 2 is true.
  • c) Both Statement (1 & 2) is wrong.
  • d) Both Statement (1 & 2) is true.

  Answer - b) Statement 1 is False and statement 2 is true

• Ensemble technique can be used for both Regression and Classification Tasks?

  • a) Possible Scenarios can be added.
  • b) True.
  • c) False.
  • d) All the above.

  Answer - b) True