Why is model evaluation important in real-world applications?

What does a confusion matrix compare?

• It compares actual and predicted classifications

Which metric measures the proportion of correct predictions out of all predictions?

• Precision
• Recall
• Accuracy
• F1 Score

In a dataset with 95% healthy patients, a model predicting all as healthy has high accuracy. Is this model useful?

What does the F1 score represent?

• Harmonic mean of precision and recall

Which metric is most useful in medical diagnosis to detect actual positives?

• Precision
• Recall
• Accuracy
• F1 Score

True or False: The AUC measures the model's ability to discriminate between classes.

What does the k in k-Nearest Neighbors (kNN) represent?

• Number of neighbors to look at

Which model building method asks yes/no questions to make decisions?

• kNN
• Decision Tree
• Logistic Regression
• Neural Network

True or False: Logistic regression assumes a non-linear relationship between features and the target.

What is a common pitfall when evaluating models?

• Only reporting accuracy

Which evaluation metric is better suited than accuracy for imbalanced datasets?

• Accuracy
• F1 Score
• None
• Both

True or False: Overfitting occurs when a model performs well on training data but poorly on new data.

Which classification model is described as easy to understand and visualize?

• kNN
• Decision Tree
• Logistic Regression
• Neural Network

What does a high precision indicate?

• Low false positives

In the context of classification, what is a false negative?

• Predicted 0, Actual 1

True or False: The goal of model evaluation is to improve the model's performance on training data only.

Which metric measures the model's ability to correctly identify actual positives?

• Precision
• Recall
• Accuracy
• F1 Score

Why is relying solely on accuracy problematic in imbalanced datasets?

• Because it can be high even if the model fails to identify minority class