Scribd
Upload
238 views4 pages

Question Bank UM19MB602: Introduction To Machine Learning Unit 4: Decision Tree

The document is a question bank for the topic of decision trees in machine learning. It contains 20 multiple choice or short answer questions about decision trees, including questions about: - What decision trees are and their importance - Why decision trees are a supervised learning algorithm - The differences between intermediate and terminal nodes - Splitting, merging, and stopping criteria for decision trees - Steps for generating decision trees using methods like CHAID and CART - Interpreting and evaluating decision tree models

Uploaded by

Bharathi Raju
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
238 views4 pages

Question Bank UM19MB602: Introduction To Machine Learning Unit 4: Decision Tree

The document is a question bank for the topic of decision trees in machine learning. It contains 20 multiple choice or short answer questions about decision trees, including questions about: - What decision trees are and their importance - Why decision trees are a supervised learning algorithm - The differences between intermediate and terminal nodes - Splitting, merging, and stopping criteria for decision trees - Steps for generating decision trees using methods like CHAID and CART - Interpreting and evaluating decision tree models

Uploaded by

Bharathi Raju
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

Question Bank

UM19MB602: Introduction to Machine Learning

Unit 4: Decision Tree

Q1. What is the decision tree in machine learning? 3M


Q2. Why is the decision tree important in machine learning? 4M
Q3. Why a decision tree is called a supervised learning algorithm? 3M
Q4. Differentiate between the intermediate node and the terminal node. 4M
Q5 Explain the following terms in the context of decision tree algorithms: 6M
i) Splitting criteria, ii) Merging criteria, iii) Stopping criteria
Q6. Write the steps used for generating a decision tree. 5M
Q7. What is the difference between CHAID and CART? 6M
Q8. When do we use the chi-square test, F-test, and likelihood ratio test for 6M
splitting the nodes in CHAID?
Q9. Write the steps used in developing a Chi-square Automatic Interaction 5M
Detection model.
Q10. 4M

How many intermediate nodes and terminal nodes we could see in the above
CHAID model?

Q11. Refer to the CHAID model in Q10, interpret the decision tree. 7M
Q12. Refer to the CHAID model in Q10. How the model algorithm has selected the 4M
feature OverTime among all other predictors to split the root node?
Q13. Use the IBM Watson employee attrition database and compute the chi-square 10M
test value for all the potential predictors.
Q14. 10M

Find out the probability of Yes and No attrition in the above CHAID terminal
nodes.
Q15. 5M

What are the approximate minsplit numbers in the above CHAID model?
Q16. 3M

What is the maxheight (stopping criteria) in the above CHAID model?

Q17. Explain the steps to develop a Classification and Regression Tree. 8M


Q18. Use the CART tree shown in the figure below to answer the following 10M
questions. The tree has been developed to predict the success of a movie
(Y=1) using the predictors budget and YouTube likes (YouTube-L).

Calculate the Gini coefficient for nodes 0, 1, 2, 3, and 4.


Q19. Refer to the CART model in Q18. What is the reduction in the Gini coefficient 5M
impurity index for the predictor’s budget and YouTube likes?
Q20. Refer to the CART model in Q18. Create business rules based on the CART 10M
Tree.

You might also like