What does recall measure in data analytics?

Recall measures the ability of a model to correctly identify true positive cases out of all actual positive cases. Specifically, it assesses the proportion of true positives (correctly predicted positive cases) to the total number of actual positives (which includes both true positives and false negatives). This metric is essential in scenarios where capturing positives is critical, as it highlights how well the model is performing in recognizing instances of the target class.

In contexts such as medical diagnosis, for example, a high recall is vital because missing a positive case (such as a disease) could have significant consequences. Thus, recall emphasizes the model's ability to spot as many actual positive instances as possible, showing its effectiveness in minimizing missed opportunities for detection.