D496 DTSC 3211
Introduction to Data Science
4.0 Credits
Objective Assessment Review (Qns &
Ans)
2025
©2025
, Question 1:
In the data science lifecycle, which phase primarily focuses on
summarizing data distributions, detecting outliers, and uncovering
underlying patterns through visual and statistical techniques?
- A. Data Wrangling
- B. Exploratory Data Analysis (EDA)
- C. Feature Engineering
- D. Model Deployment
Correct ANS: B. Exploratory Data Analysis (EDA)
Rationale:
EDA uses visualization and summary statistics to understand the data,
detect anomalies, and guide subsequent data preparation and modeling
steps.
---
Question 2:
Which term best describes the process of creating and selecting the most
informative variables from raw data to enhance model performance in
predictive analytics?
- A. Data Cleaning
- B. Feature Engineering
- C. Data Integration
- D. Data Visualization
Correct ANS: B. Feature Engineering
Rationale:
Feature engineering transforms raw data into relevant input features
that improve the predictive accuracy and robustness of machine learning
models.
---
©2025
, Question 3:
Which machine learning paradigm is most appropriate for developing
models that predict outcomes based on labeled historical data?
- A. Supervised Learning
- B. Unsupervised Learning
- C. Reinforcement Learning
- D. Transfer Learning
Correct ANS: A. Supervised Learning
Rationale:
Supervised learning trains models on labeled datasets to learn the
mapping between inputs and outputs, making it ideal for prediction
tasks.
---
Question 4:
When evaluating classification models on an imbalanced dataset, which
performance metric is generally more informative than simple accuracy?
- A. Mean Squared Error
- B. Precision-Recall AUC
- C. R-Squared
- D. Root Mean Squared Error
Correct ANS: B. Precision-Recall AUC
Rationale:
Precision-Recall AUC better reflects a classifier’s performance on
imbalanced datasets by focusing on the minority class and the trade-off
between precision and recall.
---
Question 5:
Which algorithm is primarily used for reducing the dimensionality of a
dataset by transforming it into a set of orthogonal (uncorrelated)
©2025
Introduction to Data Science
4.0 Credits
Objective Assessment Review (Qns &
Ans)
2025
©2025
, Question 1:
In the data science lifecycle, which phase primarily focuses on
summarizing data distributions, detecting outliers, and uncovering
underlying patterns through visual and statistical techniques?
- A. Data Wrangling
- B. Exploratory Data Analysis (EDA)
- C. Feature Engineering
- D. Model Deployment
Correct ANS: B. Exploratory Data Analysis (EDA)
Rationale:
EDA uses visualization and summary statistics to understand the data,
detect anomalies, and guide subsequent data preparation and modeling
steps.
---
Question 2:
Which term best describes the process of creating and selecting the most
informative variables from raw data to enhance model performance in
predictive analytics?
- A. Data Cleaning
- B. Feature Engineering
- C. Data Integration
- D. Data Visualization
Correct ANS: B. Feature Engineering
Rationale:
Feature engineering transforms raw data into relevant input features
that improve the predictive accuracy and robustness of machine learning
models.
---
©2025
, Question 3:
Which machine learning paradigm is most appropriate for developing
models that predict outcomes based on labeled historical data?
- A. Supervised Learning
- B. Unsupervised Learning
- C. Reinforcement Learning
- D. Transfer Learning
Correct ANS: A. Supervised Learning
Rationale:
Supervised learning trains models on labeled datasets to learn the
mapping between inputs and outputs, making it ideal for prediction
tasks.
---
Question 4:
When evaluating classification models on an imbalanced dataset, which
performance metric is generally more informative than simple accuracy?
- A. Mean Squared Error
- B. Precision-Recall AUC
- C. R-Squared
- D. Root Mean Squared Error
Correct ANS: B. Precision-Recall AUC
Rationale:
Precision-Recall AUC better reflects a classifier’s performance on
imbalanced datasets by focusing on the minority class and the trade-off
between precision and recall.
---
Question 5:
Which algorithm is primarily used for reducing the dimensionality of a
dataset by transforming it into a set of orthogonal (uncorrelated)
©2025
