MACHINE LEARNING FUNDAMENTALS PRACTICE
TEST 2026 QUESTIONS AND ANSWERS WITH
RATIONALES/GRADED A+/2026 UPDATE/100%
CORRECT
Domain 1: Machine Learning Fundamentals (Questions 1-15)
Q1. What is the primary goal of machine learning?
A) To program computers with explicit instructions for every possible scenario
B) To enable computers to learn from data and make predictions without being
explicitly programmed
C) To create visualizations of complex datasets
D) To design database schemas for storing large amounts of data
Answer: B
Rationale: Machine learning focuses on developing algorithms that learn patterns
from data and improve their performance through experience. Unlike traditional
programming where rules are explicitly coded, ML models identify patterns
automatically from examples.
Q2. Which type of machine learning uses labeled data to train models?
A) Unsupervised Learning
B) Reinforcement Learning
C) Supervised Learning
D) Semi-supervised Learning
Answer: C
,Rationale: Supervised learning algorithms learn from input-output pairs (labeled
data) where the correct answer is provided during training. This enables the
model to predict outputs for new, unseen inputs.
Q3. Which machine learning technique finds hidden patterns in unlabeled data
without predefined categories?
A) Supervised Learning
B) Reinforcement Learning
C) Unsupervised Learning
D) Active Learning
Answer: C
Rationale: Unsupervised learning identifies inherent structures, clusters, or
patterns in data without labeled responses. Common applications include
customer segmentation and anomaly detection.
Q4. In reinforcement learning, how does the agent learn optimal behavior?
A) By receiving labeled input-output pairs
B) By receiving rewards and penalties for actions taken in an environment
C) By clustering similar data points together
D) By reducing the dimensionality of the feature space
Answer: B
Rationale: Reinforcement learning agents learn through trial and error, receiving
positive rewards for desirable actions and negative rewards (penalties) for
undesirable ones, maximizing cumulative reward over time.
Q5. A hospital wants to predict whether a patient has a specific disease (yes/no)
based on symptoms and test results. Which ML technique should be used?
,A) Regression
B) Clustering
C) Classification
D) Dimensionality Reduction
Answer: C
Rationale: Classification predicts discrete categories or classes (yes/no, disease
present/absent). The binary outcome (disease present vs. absent) makes this a
binary classification problem.
Q6. A real estate company needs to predict house prices based on square
footage, number of bedrooms, and location. Which technique is appropriate?
A) Classification
B) Clustering
C) Regression
D) Association Rule Learning
Answer: C
Rationale: Regression predicts continuous numeric values (price). Unlike
classification which predicts categories, regression outputs a numerical quantity—
perfect for price prediction.
Q7. An e-commerce company wants to group customers with similar purchasing
behaviors without predefining categories. Which technique should they use?
A) Classification
B) Regression
C) Clustering
D) Logistic Regression
Answer: C
, Rationale: Clustering (unsupervised learning) groups similar data points without
labeled examples. Customer segmentation based on purchasing patterns is a
classic clustering application.
Q8. Despite its name, what type of problem does logistic regression solve?
A) Continuous value prediction (regression)
B) Categorical prediction (classification)
C) Grouping similar items (clustering)
D) Reducing feature dimensions
Answer: B
Rationale: Logistic regression is a CLASSIFICATION algorithm despite its name. It
predicts the probability of an instance belonging to a category (typically binary:
yes/no, true/false).
Q9. What is overfitting in machine learning?
A) Model performs poorly on both training and test data
B) Model performs well on training data but poorly on unseen data
C) Model is too simple to capture patterns in the data
D) Model trains faster than expected
Answer: B
Rationale: Overfitting occurs when a model learns noise and irrelevant details
from training data rather than general patterns. It performs excellently on training
data but fails to generalize to new, unseen data.
Q10. What is underfitting?
A) Model memorizes the training data perfectly
B) Model is too complex and captures noise
TEST 2026 QUESTIONS AND ANSWERS WITH
RATIONALES/GRADED A+/2026 UPDATE/100%
CORRECT
Domain 1: Machine Learning Fundamentals (Questions 1-15)
Q1. What is the primary goal of machine learning?
A) To program computers with explicit instructions for every possible scenario
B) To enable computers to learn from data and make predictions without being
explicitly programmed
C) To create visualizations of complex datasets
D) To design database schemas for storing large amounts of data
Answer: B
Rationale: Machine learning focuses on developing algorithms that learn patterns
from data and improve their performance through experience. Unlike traditional
programming where rules are explicitly coded, ML models identify patterns
automatically from examples.
Q2. Which type of machine learning uses labeled data to train models?
A) Unsupervised Learning
B) Reinforcement Learning
C) Supervised Learning
D) Semi-supervised Learning
Answer: C
,Rationale: Supervised learning algorithms learn from input-output pairs (labeled
data) where the correct answer is provided during training. This enables the
model to predict outputs for new, unseen inputs.
Q3. Which machine learning technique finds hidden patterns in unlabeled data
without predefined categories?
A) Supervised Learning
B) Reinforcement Learning
C) Unsupervised Learning
D) Active Learning
Answer: C
Rationale: Unsupervised learning identifies inherent structures, clusters, or
patterns in data without labeled responses. Common applications include
customer segmentation and anomaly detection.
Q4. In reinforcement learning, how does the agent learn optimal behavior?
A) By receiving labeled input-output pairs
B) By receiving rewards and penalties for actions taken in an environment
C) By clustering similar data points together
D) By reducing the dimensionality of the feature space
Answer: B
Rationale: Reinforcement learning agents learn through trial and error, receiving
positive rewards for desirable actions and negative rewards (penalties) for
undesirable ones, maximizing cumulative reward over time.
Q5. A hospital wants to predict whether a patient has a specific disease (yes/no)
based on symptoms and test results. Which ML technique should be used?
,A) Regression
B) Clustering
C) Classification
D) Dimensionality Reduction
Answer: C
Rationale: Classification predicts discrete categories or classes (yes/no, disease
present/absent). The binary outcome (disease present vs. absent) makes this a
binary classification problem.
Q6. A real estate company needs to predict house prices based on square
footage, number of bedrooms, and location. Which technique is appropriate?
A) Classification
B) Clustering
C) Regression
D) Association Rule Learning
Answer: C
Rationale: Regression predicts continuous numeric values (price). Unlike
classification which predicts categories, regression outputs a numerical quantity—
perfect for price prediction.
Q7. An e-commerce company wants to group customers with similar purchasing
behaviors without predefining categories. Which technique should they use?
A) Classification
B) Regression
C) Clustering
D) Logistic Regression
Answer: C
, Rationale: Clustering (unsupervised learning) groups similar data points without
labeled examples. Customer segmentation based on purchasing patterns is a
classic clustering application.
Q8. Despite its name, what type of problem does logistic regression solve?
A) Continuous value prediction (regression)
B) Categorical prediction (classification)
C) Grouping similar items (clustering)
D) Reducing feature dimensions
Answer: B
Rationale: Logistic regression is a CLASSIFICATION algorithm despite its name. It
predicts the probability of an instance belonging to a category (typically binary:
yes/no, true/false).
Q9. What is overfitting in machine learning?
A) Model performs poorly on both training and test data
B) Model performs well on training data but poorly on unseen data
C) Model is too simple to capture patterns in the data
D) Model trains faster than expected
Answer: B
Rationale: Overfitting occurs when a model learns noise and irrelevant details
from training data rather than general patterns. It performs excellently on training
data but fails to generalize to new, unseen data.
Q10. What is underfitting?
A) Model memorizes the training data perfectly
B) Model is too complex and captures noise
