What is the F1 Score a measure of?

The F1 Score is specifically defined as the harmonic mean of precision and recall. This metric is particularly useful in situations where there is an imbalanced class distribution, as it takes both false positives and false negatives into account. Precision measures the accuracy of the positive predictions, while recall measures the ability to find all relevant instances. By using the harmonic mean, the F1 Score balances these two metrics: it is more sensitive to lower values, providing a more comprehensive view of a model's performance than simply averaging the two.

This makes the F1 Score a valuable tool for assessing a model's performance when both precision and recall are important, especially in tasks such as classification where false positives and false negatives can carry different weights in terms of cost or significance. In contrast, other choices focus on either precision or recall individually, or suggest a simple average that does not appropriately reflect the necessary balance between the two metrics.