Font size
WorksheetsData Mining - Classification Mining
Total questions: 15
Worksheet time: 8mins
Dataset is divided into:
Training data
Evaluation data
Testing data
Answer
What is the primary purpose of a confusion matrix in classification?
To visualize the distribution of featu
To evaluate the performance of a regression model
To evaluate the performance of a classification model
To determine the correlation between features
In a confusion matrix, which cell represents the number of correctly predicted positive instances?
True Positives (TP)
False Positives (FP)
True Negatives (TN)
False Negatives (FN)
How is precision calculated from a confusion matrix?
TP / (TP + FN)
TP / (TP + FP)
(TP + TN) / (TP + FP + TN + FN)
TN / (TN + FP)
Which of the following best describes the process of selecting splits in a decision tree?
Randomly choosing features to split
Using statistical tests to determine the best split
Splitting nodes based on criteria such as Gini impurity or information gain
Selecting splits based on the smallest number of instances
What is the purpose of pruning in decision trees?
To add more branches to the tree
To remove branches that have little importance and reduce overfitting
To increase the accuracy of the tree on training data
To increase the depth of the tree
If a model has a high number of false positives, what does this indicate?
The model is predicting many true negatives correctly.
The model is incorrectly predicting negative instances as positive.
The model has a high precision.
The model has a high recall.
How can the rules generated by a decision tree be best described?
As a set of algebraic equations
As a series of if-then-else statements
As a linear regression equation
As a confusion matrix
How does class imbalance affect the confusion matrix and evaluation metrics?
It can lead to misleading accuracy, favoring the majority class
It does not affect the confusion matrix or metrics
It ensures better precision and recall
It simplifies the model building process
How does the ROC curve complement the confusion matrix in evaluating a classification model?
It visualizes the trade-off between true positive rate and false positive rate
It shows the correlation between features
It directly displays precision and recall values
It helps in tuning hyperparameters
In the provided confusion matrix, what is the number of True Positives (TP)?
50
10
5
35
According to the confusion matrix, how many False Positives (FP) are there?
(a)
What is the accuracy of the model based on the confusion matrix?
0.60
0.75
0.85
0.95
What does a higher number of False Positives (FP) indicate about the model?
It is correctly identifying negative instances as negative.
It is incorrectly predicting negative instances as positive.
It has high recall but low precision.
It has high precision but low recall.
Which of the following statements is true when using a confusion matrix to compare two models?
A model with higher accuracy will always have higher precision and recall.
A model with a higher number of True Negatives (TN) will always have a higher accuracy.
Comparing precision and recall can help determine which model performs better with imbalanced classes.
The model with the highest number of False Positives (FP) is always better.
