wayground logo

Free Printable Worksheets

Font size

S
M
L
XL
Worksheets

Regression Classification

Total questions: 38

Worksheet time: 19mins

Name
Class
Date
1.

When to use the accuracy metric?

a)

When your dataset is balanced

b)

When your dataset is unbalanced

c)

When your dataset is huge in size

d)

None of the above

2.

What are the evaluation metrics used for classification?

a)

Precision

b)

recall

c)

f1-score

d)

All of the above

3.

Which of the following are classification algorithms?

a)

Logistic Regression

b)

Linear Regression

c)

KNN

d)

Support Vector Machine

4.

In Multi-Class Classification

a)

There are 2 unique labels

b)

There are more than 2 unique labels

c)

There is only one label

d)

None of the above

5.

Logistic regression is

a)

Its regression algorithm

b)

Its binary classification algorithm

c)

Its multiclass classification algorithm

d)

None of the above

6.

When to use accuracy as an evaluation metric?

a)

When the dataset is imbalanced

b)

When the dataset is balanced

c)

When precision is more important than recall

d)

None of the above

7.

Which of the following metrics is most suitable for imbalanced datasets?

a)

Accuracy

b)

Precision

c)

Recall

d)

F1-Score

8.

Precision measures:

a)

Correctly predicted positives / Total predicted positives

b)

Correctly predicted positives / Total actual positives

c)

True positives + False negatives

d)

Total correct predictions / Total predictions

9.

Recall measures:

a)

Correctly predicted positives / Total actual positives

b)

Correctly predicted negatives / Total actual negatives

c)

False positives / True negatives

d)

Precision × Recall

10.

F1-score is the:

a)

Harmonic mean of precision and recall

b)

Arithmetic mean of precision and recall

c)

Weighted average of precision and recall

d)

None of the above

11.

In binary classification, the ROC curve plots:

a)

Precision vs Recall

b)

True Positive Rate vs False Positive Rate

c)

Accuracy vs Error rate

d)

Sensitivity vs Specificity

12.

Area under ROC curve (AUC) closer to 1 means:

a)

Poor classifier

b)

Random classifier

c)

Strong classifier

d)

None of the above

13.

Confusion matrix diagonal values represent:

a)

Incorrect classifications

b)

Correct classifications

c)

Misclassifications

d)

False predictions only

14.

Logistic Regression is:

a)

Linear regression for classification

b)

Regression for continuous values

c)

Always multi-class

d)

None of the above

15.

Logistic Regression output lies between:

a)

-∞ to +∞

b)

0 to 1

c)

-1 to +1

d)

None of the above

16.

In Logistic Regression, sigmoid function is used to:

a)

Scale features

b)

Map input to probability between 0 and 1

c)

Improve accuracy

d)

Regularize model

17.

Logistic regression can be extended to multi-class classification using:

a)

One-vs-One (OvO)

b)

One-vs-Rest (OvR)

c)

Softmax regression

d)

All of the above

18.

Which algorithm uses decision boundary based on maximizing margin?

a)

Logistic Regression

b)

SVM

c)

KNN

d)

Naïve Bayes

19.

Kernel trick in SVM is used for:

a)

Reducing dataset size

b)

Handling missing data

c)

Transforming non-linear data to higher dimensions

d)

Reducing overfitting

20.

In KNN, larger value of K leads to:

a)

High variance

b)

High bias

c)

High overfitting

d)

More complex decision boundary

21.

Which metric is most important for medical diagnosis (cancer detection)?

a)

Accuracy

b)

Precision

c)

Recall

d)

Specificity

22.

Precision is also known as:

a)

Sensitivity

b)

Specificity

c)

Positive Predictive Value

d)

Negative Predictive Value

23.

Recall is also known as:

a)

Sensitivity

b)

Specificity

c)

Accuracy

d)

False Positive Rate

24.

Which of the following can handle non-linear decision boundaries effectively?

a)

Logistic Regression

b)

Linear SVM

c)

KNN

d)

Naïve Bayes

25.

Which classification algorithm is based on Bayes’ theorem?

a)

KNN

b)

SVM

c)

Naive Bayes

d)

Logistic Regression

26.

In Naive Bayes, “naive” assumption is:

a)

All features are dependent

b)

All features are independent

c)

Features are correlated

d)

Labels are independent

27.

Which of the following is true about F1-score?

a)

High F1-score means balance between precision & recall

b)

Low F1-score means poor recall

c)

F1-score is useful in imbalanced data

d)

All of the above

28.

Which classifier works by voting mechanism?

a)

Decision Trees

b)

KNN

c)

Logistic Regression

d)

SVM

29.

Which algorithm is most interpretable for classification?

a)

Logistic Regression

b)

SVM with RBF kernel

c)

KNN

d)

Neural Networks

30.

Overfitting in KNN occurs when:

a)

K is very small

b)

K is very large

c)

Features are normalized

d)

Dataset is large

31.

Which metric penalizes false negatives more?

a)

Precision

b)

Recall

c)

Accuracy

d)

Specificity

32.

Which classification algorithm is best suited for text classification?

a)

Logistic Regression

b)

Naive Bayes

c)

SVM

d)

KNN

33.

Which classification metric is threshold-independent?

a)

ROC-AUC

b)

Accuracy

c)

Precision

d)

Recall

34.

Which classification algorithm is most prone to overfitting without regularization?

a)

Logistic Regression

b)

Decision Tree

c)

KNN

d)

Naive Bayes

35.

The decision boundary of logistic regression is always:

a)

Linear

b)

Non-linear

c)

Circular

d)

Random

36.

Softmax function in multi-class classification ensures:

a)

Each class gets probability between 0 and 1

b)

Sum of probabilities = 1

c)

One-vs-rest classification

d)

Both a and b

37.

Which of the following is most sensitive to outliers?

a)

Logistic Regression

b)

KNN

c)

Naïve Bayes

d)

SVM

38.

Which metric is used to compare the Precision and Recall trade-off?

a)

ROC curve

b)

Precision-Recall curve

c)

Confusion Matrix

d)

Specificity