Recall/ Sensitivity or True Positive Rate

The percentage of actual positives that were accurately identified is known as recall. The calculation is as follows:

Recall = True positives / True positives + False Negatives

A machine learning model's sensitivity refers to its capacity to identify positive instances. The true positive rate (TPR) or recall are other terms for it. Sensitivity is used to assess model performance since it enables us to observe how many positive instances the model could accurately detect. Few false negatives indicate a model with high sensitivity, which implies that some of the positive instances are being missed by the model. Sensitivity, in other words, assesses how well a model can identify positive examples. This is crucial because, for our models to produce reliable predictions, they must be able to identify all of the positive cases.

The sum of sensitivity (true positive rate) and false negative rate would be 1.  The model's ability to accurately detect positive cases is improved by the true positive rate.

Let’s try and understand this with the model used for predicting whether a person is suffering from the disease. Sensitivity or true positive rate is a measure of the proportion of people suffering from the disease who got predicted correctly as the ones suffering from the disease. In other words, the person who is unhealthy (positive) actually got predicted as unhealthy.

Mathematically, sensitivity or true positive rate can be calculated as the following:

Sensitivity = (True Positive)/(True Positive + False Negative)

A high sensitivity means that the model is correctly identifying most of the positive results, while a low sensitivity means that the model is missing a lot of positive results.

‍