La F-Mesure, également connue sous le nom de Score F1, is a statistical measure used to assess the performance of a classification model, particularly in scenarios with jeux de données déséquilibrés. It combines two critical métriques d’évaluation: precision and recall.
Précision refers to the number of true positive results divided by the sum of true positive and faux positif results. It indicates how many of the predicted positive instances are actually positive. Rappel, on the other hand, is the number of true positive results divided by the sum of true positive and false negative results, measuring how many of the actual positive instances were correctly identified by the model.
La F-Mesure est calculée en utilisant la formule :
F1 = 2 * (Précision * Rappel) / (Précision + Rappel)
This formula creates a single score that balances both precision and recall, providing a more comprehensive measure of a model’s accuracy than either metric alone. The F-Measure ranges from 0 to 1, where 1 indicates perfect precision and recall, and 0 indicates the worst performance.
La F-Mesure est particulièrement utile dans des applications telles que la récupération d'informations, medical diagnosis, and any other field where the cost of false positives and false negatives varies significantly. By focusing on both precision and recall, the F-Measure helps practitioners select models that are better suited to their specific needs and priorities.