ENGI 307
Data Analysis & Machine
Learning
MIDTERM EXAM REVIEW
©LU 2024/2025
,1. Multiple Choice: What is the primary difference between
supervised and unsupervised learning?
a) Supervised learning requires labeled data, while unsupervised
learning does not.
b) Unsupervised learning algorithms are computationally less
intensive.
c) Supervised learning is used only for classification problems.
d) Unsupervised learning cannot be used for predictive analytics.
Correct Answer: a) Supervised learning requires labeled data,
while unsupervised learning does not.
Rationale: Supervised learning algorithms are trained using
labeled data, i.e., input where the desired output is known.
Unsupervised learning algorithms, on the other hand, work on data
without labeled responses, with the goal to uncover hidden
patterns.
2. Fill-in-the-Blank: In a decision tree, the _______ represents the
attribute/feature that is being tested.
Correct Answer: node
Rationale: In a decision tree, each internal node represents a
"test" on an attribute, each branch represents the outcome of the
test, and each leaf node represents a class label.
©LU 2024/2025
, 3. True/False: In machine learning, feature scaling always leads to
better performance of the model.
Correct Answer: False
Rationale: Feature scaling can lead to better performance in
many algorithms that compute distances between data points, such
as k-nearest neighbors (KNN) and gradient descent-based
algorithms, but it is not universally true for all algorithms.
4. Multiple Response: Which of the following are assumptions of
linear regression? (Select all that apply)
a) Linearity
b) Homoscedasticity
c) Normal distribution of errors
d) Independence of errors
e) Fixed number of features
Correct Answers: a) Linearity, b) Homoscedasticity, c) Normal
distribution of errors, d) Independence of errors
Rationale: Linear regression assumes that there is a linear
relationship between the dependent and independent variables, the
variance of the residual is the same for any value of the
independent variable (homoscedasticity), residuals are normally
distributed, and observations are independent of each other.
©LU 2024/2025
Data Analysis & Machine
Learning
MIDTERM EXAM REVIEW
©LU 2024/2025
,1. Multiple Choice: What is the primary difference between
supervised and unsupervised learning?
a) Supervised learning requires labeled data, while unsupervised
learning does not.
b) Unsupervised learning algorithms are computationally less
intensive.
c) Supervised learning is used only for classification problems.
d) Unsupervised learning cannot be used for predictive analytics.
Correct Answer: a) Supervised learning requires labeled data,
while unsupervised learning does not.
Rationale: Supervised learning algorithms are trained using
labeled data, i.e., input where the desired output is known.
Unsupervised learning algorithms, on the other hand, work on data
without labeled responses, with the goal to uncover hidden
patterns.
2. Fill-in-the-Blank: In a decision tree, the _______ represents the
attribute/feature that is being tested.
Correct Answer: node
Rationale: In a decision tree, each internal node represents a
"test" on an attribute, each branch represents the outcome of the
test, and each leaf node represents a class label.
©LU 2024/2025
, 3. True/False: In machine learning, feature scaling always leads to
better performance of the model.
Correct Answer: False
Rationale: Feature scaling can lead to better performance in
many algorithms that compute distances between data points, such
as k-nearest neighbors (KNN) and gradient descent-based
algorithms, but it is not universally true for all algorithms.
4. Multiple Response: Which of the following are assumptions of
linear regression? (Select all that apply)
a) Linearity
b) Homoscedasticity
c) Normal distribution of errors
d) Independence of errors
e) Fixed number of features
Correct Answers: a) Linearity, b) Homoscedasticity, c) Normal
distribution of errors, d) Independence of errors
Rationale: Linear regression assumes that there is a linear
relationship between the dependent and independent variables, the
variance of the residual is the same for any value of the
independent variable (homoscedasticity), residuals are normally
distributed, and observations are independent of each other.
©LU 2024/2025
