Der F-Score, auch bekannt als F1-Score, is an Bewertungsmetrik for binärer Klassifikation models that balances precision and recall. It is particularly useful when the class distribution is imbalanced, meaning one class significantly outnumbers the other. The F-Score provides a single metric that combines both the precision (the ratio of true positive predictions to the total predicted positives) and recall (the ratio of true positive predictions to the actual positives).
Die Formel zur Berechnung des F-Score lautet:
F1-Score = 2 * (Präzision * Recall) / (Präzision + Recall)
Wo:
- Präzision: The number of true positives divided by the number of true positives plus false positives.
- Rückruf: The number of true positives divided by the number of true positives plus false negatives.
The F-Score ranges from 0 to 1, where a score of 1 indicates perfect precision and recall, while a score of 0 indicates the worst performance. An advantage of the F-Score is that it gives equal weight to precision and recall, making it more informative than accuracy allein, insbesondere in Fällen, in denen eine Klasse wichtiger ist als die andere.
In der Praxis wird der F-Score in verschiedenen Bereichen weit verbreitet eingesetzt, einschließlich der Verarbeitung natürlicher Sprache, medical diagnosis, and any domain where the cost of false positives and false negatives is significant. By optimizing for the F-Score, practitioners can ensure a more balanced approach to model evaluation and improve overall model performance.