Regression - Ai Quiz Questions

1. Suppose you have to predict the salary of an employee from their years of experience where the dataset has a salary range from 10000 to 50000. In which of the intervals your regressive model should predict?

A. 10000 to 20000

B. 10000 to 40000

C. 25000 to 50000

D. 10000 to 50000

2. In simple linear regression, if you change the input value by 1 then output value will be changed by:

A. 1

B. The slope parameter

C. The intercept parameter

D. None

3. You can compute the residual by-

A. actual y‐coordinate value - predicted y‐coordinate value

B. predicted y‐coordinate value - actual y coordinate value

C. actual y‐coordinate value / predicted y‐coordinate value

D. None

4. How to see the value of residuals geometrically

A. The perpendicular distance between a data point and the regression line

B. The euclidian distance between a data point and the regression line

C. The horizontal distance between a data point and the regression line

D. The vertical distance between a data point and the regression line

5. The equation of the regression line is y = 5x + 3. Predict y when x = 8.

A. 43

B. 53

C. 23

D. None

6. The equation of the regression line is y = 8x - 2. Compute the residual for the point (4, 28)

A. 2

B. 1

C. -2

D. 4

7. What would be the best regression model for more than one independent variable?

A. Simple Linear Regression

B. Multiple Linear Regression

C. Logistic Regression

D. All of the Above

8. Suppose you have observed that you data has an exponential growth tendency. Then what regression model you should use-

A. Simple linear regression

B. Multiple linear regression

C. Polynomial regression

D. Logistic regression

9. Can we perform linear regression with a neural network?

A. Yes, we can

B. No, we can not

C. Partially we can

D. None

10. If you get a poor accuracy using a simple linear regression model. What will be the cause behind it-

A. The data was not linear

B. The data has outliers

C. Both A or B depending on the context

D. None

11. If your data grows in a non-linear fashion. Which model won’t perform well?

A. Polynomial regression

B. Random forest regression

C. Simple linear regression

D. None

12. Suppose you got a training accuracy of 90% and a test accuracy of 50%. What happened with your model-

A. The model was over fitted with the training data

B. The model was under fitted with the training data

C. The model is absolutely fine

D. None

13. What is a support vector?

A. The average distance between all the data points

B. The distance between any two data points

C. The distance between two boundary data points

D. The minimum distance between any two data points

14. What is a kernel?

A. A function that calculates the distance of two boundary data points

B. A function that maps the value from one dimension to the other

C. A function that predicts the output value of a regression

D. None

15. Which of the following is not a kernel?

A. Polynomial Kernel

B. Gaussian Kernel

C. Sigmoid Kernel

D. None

16. What does epsilon represent in Support Vector Regression?

A. Boundary threshold

B. Error threshold

C. Distance threshold

D. None

17. In Regression, a decision tree splits the dataset based on-

A. Information entropy

B. Information gain

C. Both A and B

D. None

18. Which one is a different algorithm?

A. Logistic Regression

B. Support Vector Regression

C. Polynomial Regression

D. None

19. Which one is not a better algorithm in the sense of overfitting?

A. Simple linear regression

B. Decision tree

C. Random forest

D. All of the above

20. If the actual value of a data point is 50 and the predicted value is 55, what will be the Mean Absolute Error(MAE)

A. -5

B. 5

C. 2.5

D. -2.5

21. Which of the following is a regression algorithm?

A. Linear Regression

B. Logistic Regression

C. Both A and B

D. None

22. Suppose you have to predict the salary of employees from their experience. This is a-

A. Classification task

B. Regression task

C. Clustering task

D. None

23. Regression is a-

A. Supervised Learning Algorithm

B. Unsupervised Learning Algorithm

C. Reinforcement Learning Algorithm

D. None

24. Which of the following is/are true about Normal Equation?

The equation itself choose the learning rate

B. Becomes slower with a large number of features

C. Iteration is not required

D. All of them

25. Which methods are used to find the best fit line in linear regression?

A. Logarithmic Loss

B. Area Under Curve

C. Both A and B

D. Least Square Error

26. What will happen when you increase the size of training data?

A. Bias decreases and Variance increases

B. Bias increases and Variance increases

C. Bias increases and Variance decreases

D. Bias decreases and Variance decreases

27. If you fit 2 degree polynomial in linear regression-

A. The model will overfit the data

B. The model will underfit the data

C. The model will perform perfectly

D. None

28. Which of the following evaluation metrics can be used for Regression?

A. AUC-ROC

B. Mean-Squared-Error

C. Accuracy

D. f1 score

29. Linear regression is-

A. sensitive to outliers

B. not sensitive to outliers

C. not affected by outliers

D. None

30. What is true about Residuals?

A. Higher is better

B. Lower is better

C. A or B depending on the context

D. None

Quiz Category

Machine Learning

Artificial Intelligence

Quiz Topic - Regression