8.10 AI & ML: Model Evaluation Metrics

What are 4 metrics used to evaluate the accuracy of a binary classification?

- Precision - Recall - F1 - Accuracy

The AUC-ROC can have a value range from ______ to _______

0 to 1 (1 is a perfect model)

What are the metrics used to give the quality of a regression? (4)

1 - MAE (Mean Absolute Error) 2 - MAPE - Mean Absolute Percentage Error) 3 - RMSE - Root Mean Square Error 4 - R Squared

What are 4 metrics: - Best for balanced datasets

Accuracy

What is the AUC-ROC

Area under the curve-receiver operator curve

Evaluating email to see if it is Spam or Not Spam is an example of

Binary Classification

What are 4 metrics: - Best when false negatives are costly

Recall

The following are used to Measure ___________? 1 - MAE (Mean Absolute Error) 2 - MAPE - Mean Absolute Percentage Error) 3 - RMSE - Root Mean Square Error 4 - R Squared

Regressions

The following are used to measure __________? - Precision - Recall - F1 - Accuracy

Classification

What are 4 metrics: - Best when you want a balance between precision and Recall, especially in imbalanced datasets

F1 Score

What are 4 metrics: - Best when false positives are costly

Precision

What does a confusion Matrix compare?

Predicted Value to Actual Value

What is the primary purpose of a confusion Matrix?

To evaluate the performance of a model that does Classification