Precision and recall are performance metrics used in pattern recognition, information retrieval, object detection, and classification, particularly in machine learning. They are used to evaluate the accuracy of a models predictions by measuring how well it identifies relevant instances of a class in a dataset. Here are the definitions of precision and recall:

• Precision: The proportion of positive identifications that were actually correct. It is calculated by dividing the number of true positives by the total number of instances predicted as positive (both true and false positives) .

• Recall: The proportion of actual positives that were identified correctly. It is calculated by dividing the number of true positives by the sum of true positives and false negatives.

Precision and recall are not particularly useful metrics when used in isolation. For instance, it is possible to have perfect recall by simply retrieving every single item, or to have near-perfect precision by selecting only a very small number of extremely likely items. Therefore, they are often combined into a single measure, such as the F-measure or the Matthews correlation coefficient.

Precision and recall are used differently based on the problem requirement, and sometimes evaluating precision is wiser, while other times recall is more important. For example, in preliminary disease screening of patients for follow-up examinations, recall is usually prioritized to find all patients who actually have the disease, while precision can be lower.

It is important to track both precision and recall while evaluating a model, as there is a trade-off between them. A precision-recall curve is a plot of precision on the vertical axis and recall on the horizontal axis measured at different threshold values, which allows developers to choose the best threshold value for their model.