What is the formula for recall in a classification system?

Recall, also known as sensitivity or true positive rate, measures the ability of a classification system to identify all relevant instances within a dataset. The formula for recall is defined as the ratio of true positives to the total number of actual positives, which includes both true positives and false negatives. This can be expressed mathematically as:

Recall = True Positives / (True Positives + False Negatives)

This formula illustrates that recall focuses specifically on the instances that belong to the positive class. By capturing the proportion of correctly identified positives (true positives) in relation to all actual positives (which includes the true positives and those that were missed or incorrectly classified as negatives, i.e., the false negatives), recall provides insight into the effectiveness of a model in finding all relevant positive cases.

In contrast, the other options reflect different metrics or components related to classification systems but do not represent recall as defined in the context of evaluating model performance. Therefore, understanding the definition and calculation of recall is crucial for evaluating the performance of classification models, particularly when the cost of missing positive instances is significant.