M.Tech AI & ML Data Mining & Machine Learning Exam
2026/2027 – Practice Questions and Answers with
Rationales
SECTION A — DATA MINING FUNDAMENTALS
1. What is the primary objective of data mining?
A. Store data indefinitely
B. Discover useful patterns and knowledge from data
C. Replace databases
D. Increase network bandwidth
Answer: B
Rationale: Data mining extracts meaningful patterns, relationships,
trends, and knowledge from large datasets.
2. Data mining is commonly considered a major step within:
A. KDD
B. CPU scheduling
C. Operating-system design
D. Network routing
Answer: A
Rationale: Knowledge Discovery in Databases (KDD) includes
preprocessing, transformation, data mining, and
interpretation/evaluation.
3. Which is NOT typically a data-mining task?
A. Classification
B. Clustering
,C. Association analysis
D. Hardware manufacturing
Answer: D
Rationale: Classification, clustering, and association analysis are
standard data-mining tasks.
4. Classification is primarily:
A. Unsupervised learning
B. Supervised learning
C. Reinforcement learning
D. Random sampling
Answer: B
Rationale: Classification learns from labeled examples to assign
observations to predefined classes.
5. Clustering is generally:
A. Supervised
B. Unsupervised
C. Reinforcement-based
D. Rule-free
Answer: B
Rationale: Clustering discovers natural groups without requiring
predefined class labels.
6. Association-rule mining is mainly concerned with:
A. Relationships among items or attributes
B. Image segmentation
C. Neural-network initialization
D. Operating-system scheduling
,Answer: A
Rationale: Association mining discovers co-occurrence relationships
such as products frequently purchased together.
7. Which is an example of data mining?
A. Discovering customers likely to churn
B. Installing a hard drive
C. Formatting a disk
D. Compiling source code
Answer: A
Rationale: Predicting customer churn from historical patterns is a
typical data-mining application.
8. Descriptive data mining primarily:
A. Describes patterns in existing data
B. Predicts only future values
C. Controls robots
D. Encrypts information
Answer: A
Rationale: Descriptive mining summarizes and characterizes existing
datasets.
9. Predictive mining focuses on:
A. Estimating unknown or future outcomes
B. Deleting duplicate records
C. Compressing databases
D. Creating network connections
Answer: A
Rationale: Predictive methods use existing data to estimate future or
unknown outcomes.
, 10. A data warehouse is designed primarily for:
A. Analytical processing
B. Operating-system booting
C. CPU control
D. Password generation
Answer: A
Rationale: Data warehouses integrate historical data for analysis,
reporting, and decision support.
11. OLAP stands for:
A. Online Analytical Processing
B. Online Algorithmic Prediction
C. Operational Learning and Processing
D. Object-Level Analysis Protocol
Answer: A
Rationale: OLAP enables multidimensional analysis of business and
organizational data.
12. ETL stands for:
A. Extract, Transform, Load
B. Evaluate, Train, Learn
C. Encode, Test, Label
D. Extract, Transfer, Link
Answer: A
Rationale: ETL pipelines extract data from sources, transform it, and
load it into a target system.
13. Data preprocessing is important because:
A. Real-world data often contains noise and inconsistencies
B. All data is always perfect
2026/2027 – Practice Questions and Answers with
Rationales
SECTION A — DATA MINING FUNDAMENTALS
1. What is the primary objective of data mining?
A. Store data indefinitely
B. Discover useful patterns and knowledge from data
C. Replace databases
D. Increase network bandwidth
Answer: B
Rationale: Data mining extracts meaningful patterns, relationships,
trends, and knowledge from large datasets.
2. Data mining is commonly considered a major step within:
A. KDD
B. CPU scheduling
C. Operating-system design
D. Network routing
Answer: A
Rationale: Knowledge Discovery in Databases (KDD) includes
preprocessing, transformation, data mining, and
interpretation/evaluation.
3. Which is NOT typically a data-mining task?
A. Classification
B. Clustering
,C. Association analysis
D. Hardware manufacturing
Answer: D
Rationale: Classification, clustering, and association analysis are
standard data-mining tasks.
4. Classification is primarily:
A. Unsupervised learning
B. Supervised learning
C. Reinforcement learning
D. Random sampling
Answer: B
Rationale: Classification learns from labeled examples to assign
observations to predefined classes.
5. Clustering is generally:
A. Supervised
B. Unsupervised
C. Reinforcement-based
D. Rule-free
Answer: B
Rationale: Clustering discovers natural groups without requiring
predefined class labels.
6. Association-rule mining is mainly concerned with:
A. Relationships among items or attributes
B. Image segmentation
C. Neural-network initialization
D. Operating-system scheduling
,Answer: A
Rationale: Association mining discovers co-occurrence relationships
such as products frequently purchased together.
7. Which is an example of data mining?
A. Discovering customers likely to churn
B. Installing a hard drive
C. Formatting a disk
D. Compiling source code
Answer: A
Rationale: Predicting customer churn from historical patterns is a
typical data-mining application.
8. Descriptive data mining primarily:
A. Describes patterns in existing data
B. Predicts only future values
C. Controls robots
D. Encrypts information
Answer: A
Rationale: Descriptive mining summarizes and characterizes existing
datasets.
9. Predictive mining focuses on:
A. Estimating unknown or future outcomes
B. Deleting duplicate records
C. Compressing databases
D. Creating network connections
Answer: A
Rationale: Predictive methods use existing data to estimate future or
unknown outcomes.
, 10. A data warehouse is designed primarily for:
A. Analytical processing
B. Operating-system booting
C. CPU control
D. Password generation
Answer: A
Rationale: Data warehouses integrate historical data for analysis,
reporting, and decision support.
11. OLAP stands for:
A. Online Analytical Processing
B. Online Algorithmic Prediction
C. Operational Learning and Processing
D. Object-Level Analysis Protocol
Answer: A
Rationale: OLAP enables multidimensional analysis of business and
organizational data.
12. ETL stands for:
A. Extract, Transform, Load
B. Evaluate, Train, Learn
C. Encode, Test, Label
D. Extract, Transfer, Link
Answer: A
Rationale: ETL pipelines extract data from sources, transform it, and
load it into a target system.
13. Data preprocessing is important because:
A. Real-world data often contains noise and inconsistencies
B. All data is always perfect
