1. What does a learning curve represent in machine learning?
A. The accuracy of the model during training
B. The change in the model's performance over time
C. The increase in model complexity during training
D. The error as the model learns over iterations or epochs
Answer: D) The error as the model learns over iterations or epochs
Rationale: A learning curve plots the model's performance (such as error) over time or
iterations, showing how the model improves as it is trained.
2. In which scenario would you use a time series analysis?
A. Predicting the price of a stock based on its historical prices
B. Grouping customers based on purchasing behavior
C. Classifying email as spam or not spam
D. Recommending movies based on user preferences
Answer: A) Predicting the price of a stock based on its historical prices
Rationale: Time series analysis is specifically used to analyze data points ordered in
time, like predicting stock prices.
,3. Which of the following metrics is used for evaluating the performance of a binary
classification model?
A. Accuracy
B. Mean Absolute Error (MAE)
C. Precision, Recall, and F1-Score
D. R-squared
Answer: C) Precision, Recall, and F1-Score
Rationale: Precision, Recall, and F1-Score are commonly used to evaluate binary
classification models, especially when dealing with imbalanced classes.
4. Which of the following is true about the "Naive" in Naive Bayes?
A. The model assumes that the features are dependent on each other.
B. The model assumes that all features are equally important.
C. The model assumes that features are independent of each other.
D. The model does not require any prior probabilities.
Answer: C) The model assumes that features are independent of each other.
Rationale: The term "naive" comes from the assumption that all features are
independent, which simplifies the computation but is often unrealistic.
, 5. Which of the following algorithms is often used for feature selection in high-
dimensional datasets?
A. Linear Regression
B. Lasso Regression
C. Random Forest
D. K-Means Clustering
Answer: B) Lasso Regression
Rationale: Lasso regression uses L1 regularization, which can shrink coefficients to
zero, effectively performing feature selection in high-dimensional data.
6. Which metric is most commonly used to evaluate the performance of a regression
model?
A. Accuracy
B. Precision
C. Mean Squared Error (MSE)
D. F1-Score
Answer: C) Mean Squared Error (MSE)
A. The accuracy of the model during training
B. The change in the model's performance over time
C. The increase in model complexity during training
D. The error as the model learns over iterations or epochs
Answer: D) The error as the model learns over iterations or epochs
Rationale: A learning curve plots the model's performance (such as error) over time or
iterations, showing how the model improves as it is trained.
2. In which scenario would you use a time series analysis?
A. Predicting the price of a stock based on its historical prices
B. Grouping customers based on purchasing behavior
C. Classifying email as spam or not spam
D. Recommending movies based on user preferences
Answer: A) Predicting the price of a stock based on its historical prices
Rationale: Time series analysis is specifically used to analyze data points ordered in
time, like predicting stock prices.
,3. Which of the following metrics is used for evaluating the performance of a binary
classification model?
A. Accuracy
B. Mean Absolute Error (MAE)
C. Precision, Recall, and F1-Score
D. R-squared
Answer: C) Precision, Recall, and F1-Score
Rationale: Precision, Recall, and F1-Score are commonly used to evaluate binary
classification models, especially when dealing with imbalanced classes.
4. Which of the following is true about the "Naive" in Naive Bayes?
A. The model assumes that the features are dependent on each other.
B. The model assumes that all features are equally important.
C. The model assumes that features are independent of each other.
D. The model does not require any prior probabilities.
Answer: C) The model assumes that features are independent of each other.
Rationale: The term "naive" comes from the assumption that all features are
independent, which simplifies the computation but is often unrealistic.
, 5. Which of the following algorithms is often used for feature selection in high-
dimensional datasets?
A. Linear Regression
B. Lasso Regression
C. Random Forest
D. K-Means Clustering
Answer: B) Lasso Regression
Rationale: Lasso regression uses L1 regularization, which can shrink coefficients to
zero, effectively performing feature selection in high-dimensional data.
6. Which metric is most commonly used to evaluate the performance of a regression
model?
A. Accuracy
B. Precision
C. Mean Squared Error (MSE)
D. F1-Score
Answer: C) Mean Squared Error (MSE)
