wayground logo

Free Printable Worksheets

Font size

S
M
L
XL
Worksheets

ML OVERVIEW

Total questions: 65

Worksheet time: 37mins

Name
Class
Date
1.

What is the primary goal of machine learning?

a)

Write explicit programs for tasks

b)

Automate analytical model building

c)

Store large amounts of data

d)

Perform arithmetic calculations

2.

Which of the following is NOT a type of machine learning?

a)

 Supervised Learning

b)

Unsupervised Learning

c)

Reinforcement Learning

d)

Deterministic Learning

3.

Which of the following is an example of supervised learning?

a)

Clustering customers by behavior

b)

Classifying emails as spam or not spam

c)

Reducing image dimensions

d)

Detecting network anomalies

4.

What type of learning involves discovering hidden patterns in data without labels?

a)

Supervised Learning

b)

Semi-supervised Learning

c)

Unsupervised Learning

d)

Reinforcement Learning

5.

Which application is NOT a typical use case of machine learning?

a)

Fraud detection

b)

Prediction of equipment failures

c)

Generating prime numbers

d)

Recommendation engines

6.

What are the two main types of supervised learning?

a)

Regression and Classification

b)

 Clustering and Dimensionality Reduction

c)

Regression and Clustering

d)

Anomaly Detection and Classification

7.

What algorithm is commonly used for classification tasks?

a)

Principal Component Analysis

b)

Linear Regression

c)

Logistic Regression

d)

 K-Means Clustering

8.

In supervised learning, the dataset contains:

a)

Only input features

b)

Only output labels

c)

Input features and corresponding output labels

d)

No labeled data

9.

Which of the following is an example of a regression problem?

a)

 Predicting house prices

b)

Detecting spam emails

c)

Grouping customers by behavior

d)

Recommending movies

10.

Which is NOT an example of supervised learning?

a)

Predicting stock prices

b)

 Fraud detection

c)

Customer segmentation

d)

Spam email detection

11.

Which technique is used for dimensionality reduction in unsupervised learning?

a)

 Logistic Regression

b)

Principal Component Analysis

c)

 Random Forest

d)

Gradient Descent

12.

What is the primary goal of clustering in unsupervised learning?

a)

 Predicting output values

b)

Reducing features in a dataset

c)

Grouping similar data points

d)

Detecting anomalies

13.

Which algorithm is used for clustering tasks?

a)

K-Means

b)

Decision Trees

c)

Logistic Regression

d)

Random Forest

14.

Which of the following is NOT an unsupervised learning task?

a)

Clustering

b)

 Dimensionality Reduction

c)

Anomaly Detection

d)

Predicting house prices

15.

What type of unsupervised learning involves detecting outliers?

a)

Dimensionality Reduction

b)

Clustering

c)

Anomaly Detection

d)

Classification

16.

What happens when a model overfits?

a)

 It captures the general pattern but not the details

b)

It performs well on test data but poorly on training data

c)

It learns noise and performs poorly on new data

d)

 It is too simple to capture patterns in the data

17.

Underfitting occurs when:

a)

The model is too complex

b)

The model captures noise instead of patterns

c)

The model is too simple to learn patterns

d)

There are too many features in the dataset

18.

Which of the following is a sign of overfitting?

a)

High training accuracy and high test accuracy

b)

Low training accuracy and high test accuracy

c)

 High training accuracy and low test accuracy

d)

Low training accuracy and low test accuracy

19.

What can help reduce underfitting?

a)

Simplifying the model

b)

Increasing the training time

c)

Reducing the number of features

d)

 Adding more data

20.

Which is NOT a common cause of overfitting?

a)

Too many features

b)

Training the model for too many iterations

c)

Insufficient training data

d)

 Using simpler models

21.

The confusion matrix is used to:

a)

Evaluate regression models

b)

Measure the variance of predictions

c)

Compare actual and predicted values in classification

d)

Select hyperparameters

22.

What does the True Positive (TP) in a confusion matrix represent?

a)

Incorrectly predicted positives

b)

Correctly predicted negatives

c)

Correctly predicted positives

d)

Incorrectly predicted negatives

23.

Precision measures:

a)

How many actual positives were correctly identified

b)

How many predicted positives are actually positive

c)

The proportion of errors in the predictions

d)

The ability of the model to generalize

24.

Which of the following metrics balances precision and recall?

a)

Accuracy

b)

 F1 Score

c)

Recall

d)

Precision

25.

Mean Squared Error (MSE) gives more weight to:

a)

 Smaller errors

b)

Larger errors

c)

Average errors

d)

No errors

26.

What is the primary advantage of Root Mean Squared Error (RMSE)?

a)

It treats all errors equally

b)

It has the same scale as the target variable

c)

 It is unaffected by outliers

d)

 It is easier to calculate than MSE

27.

R-squared (R²) measures:

a)

 The variance in independent variables

b)

The variance explained by the model

c)

The total error in predictions

d)

The average of absolute errors

28.

Which metric is sensitive to outliers?

a)

Mean Absolute Error (MAE)

b)

Mean Squared Error (MSE)

c)

 R-squared (R²)

d)

 Accuracy

29.

What does an R² score of 0 indicate?

a)

The model perfectly predicts the data

b)

The model performs worse than the mean

c)

The model performs no better than the mean

d)

The model performs perfectly on training data

30.

Which application is an example of clustering?

a)

 Predicting stock prices

b)

Grouping customers based on purchase behavior

c)

Classifying emails as spam

d)

 Detecting fraudulent transactions

31.

Which task involves anomaly detection?

a)

Customer segmentation

b)

Fraud detection

c)

Predicting house prices

d)

Sentiment analysis

32.

Which is an example of supervised learning?

a)

 Predicting credit scores

b)

Segmenting customer groups

c)

Reducing image size

d)

 Detecting anomalies

33.

Text sentiment analysis is an example of:

a)

 Clustering

b)

Regression

c)

Classification

d)

Dimensionality reduction

34.

Overfitting occurs when a model learns the ___ and ___ in the training data, resulting in poor generalization to new data.

(a)  

35.

Unsupervised learning aims to identify ___ and ___ in data without the use of labeled outputs.

(a)  

36.

In supervised learning, ___ algorithms predict continuous values, while ___ algorithms predict discrete categories.


(a)  

37.

The (a)   is the harmonic mean of precision and recall.

38.

K-Means, DBSCAN, and hierarchical clustering are common algorithms used for (a)   in unsupervised learning.

39.

Mean Absolute Error (MAE) measures the average of the (a)   differences between predicted and actual values.

40.

Dimensionality reduction is often used for ___ and ___ in machine learning.

(a)  

41.

An R² score of (a)   indicates that the model perfectly fits the data.

42.

Supervised learning requires labeled data for training.

a)

True

b)

False

43.

A high accuracy score always indicates a good model.

a)

true

b)

false

44.

Overfitting occurs when a model is too simple for the given data.

a)

True

b)

False

45.

Recall measures the proportion of actual positives correctly identified.

a)

True

b)

False

46.

PCA is an algorithm used for clustering in unsupervised learning.

a)

true

b)

false

47.

The Mean Squared Error (MSE) gives more weight to larger errors compared to MAE.

a)

True

b)

False

48.

What is the main characteristic of supervised learning?

a)

No labeled data is used

b)

Both input and corresponding outputs are used

c)

Only input data is provided

d)

Patterns are detected automatically

49.
  1. In supervised learning, which of the following algorithms is used for regression tasks?

a)

Logistic Regression

b)

Decision Trees

c)

K-Means Clustering

d)

PCA

50.

Which of the following is a primary task of unsupervised learning?

a)

Classification

b)

Clustering

c)

 Regression

d)

Prediction

51.

What kind of data is used in unsupervised learning?

a)

Data with labels

b)

Data without labels

c)

Data with missing values

d)

Data with continuous outputs

52.

A model achieves 99% accuracy on training data but only 50% accuracy on test data. What is the issue?

a)

Underfitting

b)

 Overfitting

c)

Poor Data Cleaning

d)

High Bias

53.

What is the formula for Recall?

a)

TP / (TP + FP)

b)

TP / (TP + FN)

c)

FP / (FP + TP)

d)

TN / (TN + FP)

54.

What is the purpose of splitting data into training and test sets?

a)
  • To avoid data leakage

b)
  • To optimize model parameters

c)
  • To evaluate the model's performance on unseen data

d)

To improve training accuracy

55.

What is the feedback loop in the machine learning process used for?

a)

 To improve test set performance

b)

To tweak the model and re-train if the performance is poor

c)

To deploy the model

d)

 To validate the final model

56.

Which unsupervised learning algorithm would you use to group customers based on purchasing behavior?

a)

Decision Trees

b)

K-Means

c)

 Logistic Regression

d)

PCA

57.

What is the main purpose of dimensionality reduction?

a)

Predict categorical values

b)

Improve training speed and visualization

c)

 Increase the number of features

d)

Reduce overfitting

58.

Which of the following is NOT an unsupervised learning application?

a)

Customer segmentation

b)

Fraud detection

c)

Anomaly detection

d)

 Dimensionality reduction

59.

Which regression metric gives higher weight to larger errors?

a)
  • MAE

b)

MSE

c)

Accuracy

d)

R-Squared

60.

A regression model has an R² score of -0.5. What does this indicate?

a)

The model is overfitting

b)

The model is better than the mean

c)
  • The model performs worse than predicting the mean

d)

The model is perfect

61.

What is the first step in the Machine Learning Process?

a)

Data Cleaning

b)

Data Acquisition

c)

Model Deployment

d)

Model Testing

62.

Which step directly follows "Model Training & Building"?

a)

Data Acquisition

b)

Model Deployment

c)

Model Testing

d)

Data Cleaning

63.

What is the purpose of the Test Data step?

a)

To train the model

b)

To evaluate the model’s generalization performance

c)

To clean the raw data

d)

To deploy the model into production

64.

In which step does the model interact with real-world data?

a)

Model Testing

b)

Model Training & Building

c)

Data Cleaning

d)

 Model Deployment

65.

What is the role of "Data Cleaning" in the Machine Learning Process?

a)

 It evaluates the model’s accuracy

b)

It removes noise and prepares data for training

c)

It splits the data into training and testing sets

d)

It adjusts model hyperparameters