Akansha Yadav explains recall, also called sensitivity, a metric that measures how many actual positive instances a model catches. Recall is calculated as TP / (TP + FN), where TP is true positives and FN is false negatives. It answers: of all the real positives, how many did the model find?
So let's see what is recall and sensitivity in machine learning and how to calculate it using confusion matrix. So confusion matrix gives us the 4 values: TP, FN, TN, FP. And recall and sensitivity is basically— it will tell you the coverage of the actual positive samples. What, like, what is the coverage of the actual positive samples? To calculate it, what you have to do is you have to do true positive divided by true positive plus false negative. This will give you the value of recall and sensitivity.
