Question

When evaluating machine learning model performance, which metric specifically measures the proportion of actual positive cases that were correctly identified by the model?

Accepted Answer

The metric that measures the proportion of actual positive cases correctly identified by a model is called Recall, also known as Sensitivity or the True Positive Rate. To calculate Recall, you divide the number of True Positives by the total number of Actual Positives. A True Positive is an instance where the model correctly predicted a positive outcome for a case that is truly positive. The Actual Positives represent the sum of all cases that are truly positive, which includes both the True Positives and the False Negatives. A False Negative occurs when a model incorrectly predicts a negative outcome for a case that is actually positive. For example, in a medical test designed to detect a specific disease, Recall identifies the percentage of all sick patients that the test successfully flagged. If there are 100 sick patients and the model correctly identifies 80 of them, the Recall is 80 percent. This metric is essential when the cost of missing a positive case is high, as it prioritizes capturing as many actual positive instances as possible.

Home → All Courses → Engineering and Technology Courses → Product Management Engineering → Flashcard

When evaluating machine learning model performance, which metric specifically measures the proportion of actual positive cases that were correctly identified by the model?