NEW
Font size
S
M
L
XL
WorksheetsData Sceince MCQS
Total questions: 80
Worksheet time: 40mins
Name
Class
Date
1.
Which of the following best describes data mining?
a)
The process of cleaning data
b)
The process of discovering patterns in large datasets
c)
Storing data in a spreadsheet
d)
Deleting duplicate records
2.
What is the key difference between supervised and unsupervised learning?
a)
Supervised uses labels; unsupervised does not
b)
Unsupervised uses labels; supervised does not
c)
Both use labels
d)
Neither uses labels
3.
What is the primary goal of regression analysis?
a)
To predict a categorical outcome
b)
To predict a continuous numerical outcome
c)
To cluster data
d)
To reduce dimensionality
4.
Which structure is inspired by the human brain and used in deep learning?
a)
Decision tree
b)
Neural network
c)
Linear regression
d)
K-means
5.
Which of the following is NOT one of the 5 Vs of Big Data?
a)
Volume
b)
Velocity
c)
Variety
d)
Visibility
6.
What does data normalization in databases primarily achieve?
a)
Adds redundancy
b)
Reduces redundancy and improves integrity
c)
Increases storage size
d)
Slows down queries
7.
Which term refers to the graphical representation of information and data?
a)
Data cleaning
b)
Data visualization
c)
Data mining
d)
Data wrangling
8.
In machine learning a decision tree is used for:
a)
Clustering only
b)
Classification and regression
c)
Only visualization
d)
Only data cleaning
9.
What problem arises when a model learns the training data too closely including noise?
a)
Underfitting
b)
Overfitting
c)
Regularization
d)
Dimensionality reduction
10.
What is the main purpose of cross-validation in model training?
a)
To increase model complexity
b)
To assess model generalization
c)
To speed up training
d)
To reduce features
11.
A confusion matrix is used to evaluate the performance of a:
a)
Clustering algorithm
b)
Classification model
c)
Regression model
d)
Database query
12.
Which field combines linguistics and computer science to enable machines to understand human language?
a)
Data warehousing
b)
Natural Language Processing (NLP)
c)
Image processing
d)
Network security
13.
Feature selection in machine learning aims to:
a)
Add more features
b)
Reduce overfitting by removing irrelevant features
c)
Increase model complexity
d)
Ignore data quality
14.
Which system suggests products or content to users based on their preferences?
a)
Database engine
b)
Recommender system
c)
ETL pipeline
d)
Neural network layer
15.
Clustering is an example of which type of learning?
a)
Reinforcement learning
b)
Unsupervised learning
c)
Supervised learning
d)
Semi-supervised learning
16.
Principal Component Analysis (PCA) is primarily used for:
a)
Clustering
b)
Dimensionality reduction
c)
Regression
d)
Encryption
17.
Which technique analyzes data points collected over time to forecast future values?
a)
Cross-validation
b)
Time series analysis
c)
Clustering
d)
Text mining
18.
Which algorithm is commonly used for classification and regression in data mining?
a)
Apriori
b)
K-means
c)
Decision tree
d)
ETL
19.
An expert system mimics human expertise to solve problems in a specific domain using:
a)
Random guessing
b)
Rule-based knowledge and inference
c)
Unsupervised learning
d)
Physical sensors
20.
What does CRISP-DM stand for?
a)
Cross-industry standard process for data mining
b)
Computerized retrieval of information systems protocol
c)
Customer relationship information system process
d)
Centralized repository for integrated statistical processing
21.
The K-means algorithm partitions data into groups by minimizing:
a)
Variance within clusters
b)
Distance to origin
c)
Number of features
d)
Time complexity
22.
Which role focuses more on storytelling and business insights compared to building complex models?
a)
Data engineer
b)
Data analyst
c)
Data scientist
d)
Database administrator
23.
In data warehousing ETL stands for:
a)
Encrypt Transform Load
b)
Extract Transform Load
c)
Evaluate Test Learn
d)
Estimate Translate Log
24.
Hadoop is primarily used for:
a)
Real-time processing
b)
Storing and processing large-scale distributed datasets
c)
Graphical visualization
d)
Mobile app development
25.
A predictive model uses historical data to:
a)
Describe past events only
b)
Forecast future outcomes
c)
Delete old records
d)
Increase data volume
26.
In a neural network each layer transforms its input data into a(n):
a)
Higher-dimensional space
b)
More abstract representation
c)
Smaller file size
d)
Random noise
27.
In classification tasks accuracy is defined as:
a)
True positives divided by total predictions
b)
True positives plus true negatives divided by total predictions
c)
True positives divided by false positives
d)
False negatives divided by true positives
28.
Precision in classification is calculated as:
a)
True positives divided by false negatives
b)
True positives divided by false positives
c)
True positives divided by true positives plus false positives
d)
True negatives divided by total predictions
29.
Which metric balances precision and recall using their harmonic mean?
a)
Accuracy
b)
F1-score
c)
ROC-AUC
d)
Mean squared error
30.
Over-sampling in imbalanced datasets is used to:
a)
Reduce the majority class
b)
Increase the minority class
c)
Delete outliers
d)
Lower dimensionality
31.
Which distance measure does K-means clustering typically use?
a)
Hamming distance
b)
Euclidean distance
c)
Manhattan distance
d)
Cosine distance
32.
A ROC curve plots:
a)
Precision vs recall
b)
True positive rate vs false positive rate
c)
Accuracy vs F1-score
d)
Loss vs epoch
33.
Which library in Python is most associated with data manipulation and analysis?
a)
TensorFlow
b)
Pandas
c)
Flask
d)
Django
34.
Which of the following is a tree-based ensemble method?
a)
Linear regression
b)
K-nearest neighbors
c)
Random forest
d)
Naive Bayes
35.
Which technique reduces overfitting by penalizing large coefficients?
a)
Bagging
b)
Boosting
c)
Regularization
d)
Clustering
36.
Which of the following is NOT a type of regression?
a)
Linear
b)
Logistic
c)
Polynomial
d)
Ridge
37.
Which algorithm is based on Bayes’ theorem and assumes feature independence?
a)
Decision tree
b)
Naive Bayes
c)
Support vector machine
d)
K-means
38.
Which method is commonly used to handle missing numerical data?
a)
Mean imputation
b)
One-hot encoding
c)
Principal component analysis
d)
Tokenization
39.
Which visualization is best suited for showing relationships between two continuous variables?
a)
Bar chart
b)
Histogram
c)
Scatter plot
d)
Pie chart
40.
Which of the following is an unsupervised dimensionality reduction technique?
a)
t-SNE
b)
Linear regression
c)
Logistic regression
d)
Decision tree
41.
Which activation function outputs values between 0 and 1?
a)
ReLU
b)
Tanh
c)
Sigmoid
d)
Leaky ReLU
42.
Which layer in a CNN is responsible for detecting edges and textures in images?
a)
Fully connected
b)
Pooling
c)
Convolutional
d)
Dropout
43.
Which optimizer adapts learning rates for each parameter during training?
a)
SGD
b)
Adam
c)
RMSprop
d)
Adagrad
44.
Which evaluation metric is appropriate for regression tasks?
a)
Accuracy
b)
Mean squared error
c)
Precision
d)
F1-score
45.
Which technique splits data into training and testing sets multiple times to ensure robust evaluation?
a)
Hold-out validation
b)
K-fold cross-validation
c)
Leave-one-out encoding
d)
Bootstrap sampling
46.
Which of the following is a generative model?
a)
Logistic regression
b)
Naive Bayes
c)
Support vector machine
d)
Random forest
47.
Which algorithm clusters data by finding dense regions separated by sparse regions?
a)
DBSCAN
b)
K-means
c)
Hierarchical
d)
Gaussian mixture
48.
Which method assigns new data points to the nearest centroid?
a)
K-means
b)
Decision tree
c)
Linear regression
d)
Apriori
49.
Which of the following is NOT a hyperparameter of a decision tree?
a)
Max depth
b)
Min samples split
c)
Learning rate
d)
Min samples leaf
50.
Which technique combines weak learners to form a strong learner?
a)
Ensemble learning
b)
Overfitting
c)
Underfitting
d)
Feature scaling
51.
Which of the following is used for frequent pattern mining in transactional data?
a)
Apriori
b)
K-means
c)
PCA
d)
Linear regression
52.
Which loss function is commonly used for binary classification?
a)
Mean squared error
b)
Hinge loss
c)
Binary cross-entropy
d)
Huber loss
53.
Which of the following is a disadvantage of the k-NN algorithm?
a)
Fast on large datasets
b)
Not affected by irrelevant features
c)
Sensitive to feature scaling
d)
Low memory usage
54.
Which technique reduces dimensionality by projecting data onto eigenvectors?
a)
t-SNE
b)
PCA
c)
ICA
d)
LDA
55.
Which of the following models uses support vectors to find the optimal hyperplane?
a)
Decision tree
b)
Random forest
c)
SVM
d)
Naive Bayes
56.
Which metric measures the proportion of actual positives correctly identified?
a)
Precision
b)
Recall
c)
Specificity
d)
Accuracy
57.
Which regularization technique adds the absolute value of coefficients to the loss function?
a)
L1
b)
L2
c)
Elastic Net
d)
Dropout
58.
Which of the following is used for sequence-to-sequence modeling in NLP?
a)
CNN
b)
RNN
c)
LSTM
d)
Decision tree
59.
Which of the following is a transformer-based language model?
a)
Word2Vec
b)
GloVe
c)
BERT
d)
TF-IDF
60.
Which technique converts categorical variables into numerical format?
a)
Feature scaling
b)
One-hot encoding
c)
Normalization
d)
Standardization
61.
Which of the following is a common method for evaluating clustering quality?
a)
Silhouette score
b)
Accuracy
c)
F1-score
d)
AUC-ROC
62.
Which of the following is a time series decomposition component?
a)
Mean squared error
b)
Trend
c)
Precision
d)
Recall
63.
Which algorithm is used for association rule learning?
a)
Apriori
b)
K-means
c)
Linear regression
d)
PCA
64.
Which of the following is a deep learning framework?
a)
Scikit-learn
b)
TensorFlow
c)
Pandas
d)
Matplotlib
65.
Which technique mitigates multicollinearity in regression?
a)
Ridge regression
b)
Decision tree
c)
K-means
d)
Naive Bayes
66.
Which of the following is a disadvantage of deep neural networks?
a)
Require large datasets
b)
Cannot learn complex patterns
c)
Slow inference
d)
Cannot use GPUs
67.
Which of the following is used for hyperparameter tuning?
a)
Grid search
b)
Standardization
c)
Normalization
d)
Feature selection
68.
Which of the following is a type of ensemble learning?
a)
Bagging
b)
Normalization
c)
Regularization
d)
Feature scaling
69.
Which of the following is a Python library for neural networks?
a)
Keras
b)
NumPy
c)
SciPy
d)
Pandas
70.
Which of the following is used for text vectorization?
a)
TF-IDF
b)
PCA
c)
K-means
d)
Ridge
71.
Which of the following is a measure of model complexity influenced by the number of features?
a)
Bias
b)
Variance
c)
Loss
d)
Epoch
72.
Which of the following is a common step in EDA (Exploratory Data Analysis)?
a)
Feature engineering
b)
Model deployment
c)
Data visualization
d)
Hyperparameter tuning
73.
Which of the following is a method to handle imbalanced datasets?
a)
SMOTE
b)
PCA
c)
t-SNE
d)
Apriori
74.
Which of the following is a type of neural network layer that prevents overfitting?
a)
ReLU
b)
Dropout
c)
Convolutional
d)
Sigmoid
75.
Which of the following is a metric for regression model performance?
a)
R-squared
b)
Accuracy
c)
F1-score
d)
Precision
76.
Which of the following is used for distributed deep learning?
a)
Hadoop
b)
Spark
c)
Horovod
d)
Flask
77.
Which of the following is a characteristic of Big Data analytics?
a)
Small sample size
b)
Structured data only
c)
Scalability
d)
Single machine processing
78.
Which of the following is a technique for handling categorical variables with high cardinality?
a)
One-hot encoding
b)
Target encoding
c)
Standardization
d)
Min-max scaling
79.
Which of the following is a common activation function in hidden layers?
a)
Sigmoid
b)
ReLU
c)
Softmax
d)
Linear
80.
Which of the following is a method to prevent overfitting in decision trees?
a)
Pruning
b)
Boosting
c)
Stacking
d)
Bagging
Reset
