Rückruf, also known as sensitivity or true positive rate, is a key performance metric used to evaluate the effectiveness of a classification model in the Bereich der künstlichen Intelligenz verwendet wird and maschinellem Lernen. It quantifies the ability of a model to correctly identify all relevant instances within a dataset.
Mathematisch wird Recall als das Verhältnis der True Positives zu der Gesamtzahl der tatsächlichen positiven Instanzen definiert. Die Formel für Recall lautet:
Rückruf = Wahre Positive / (Wahre Positive + Falsche Negative)
In dieser Formel:
- Wahre Positive (TP) beziehen sich auf die Instanzen, die korrekt als positiv klassifiziert wurden.
- Falsche Negative (FN) are the instances that are incorrectly classified as negative, despite being positive.
Recall is particularly important in scenarios where the cost of missing a positive instance is high, such as in medical diagnoses or Betrugserkennung. A high recall score indicates that the model is effective at capturing most of the relevant instances, while a low score suggests that many positive instances are being overlooked.
However, it is essential to consider recall in conjunction with other metrics, such as precision (the ratio of true positives to the total predicted positives) and F1 score (the harmonisches Mittel of precision and recall), to get a comprehensive understanding of a model’s performance. Balancing recall and precision is crucial, as focusing solely on maximizing recall may lead to a high number of false positives.