Recall (EN)

Concept

Metric indicating how many of the actual positive instances were correctly identified

Recall in the classification process

flowchart TD     A[All Cases] --> B[Positive Cases]     A --> C[Negative Cases]     B --> D[True Positives]     B --> E[False Negatives]     C --> F[True Negatives]     C --> G[False Positives]          D --> H[Correctly identified positive cases]     E --> H[Missed positive cases]          H --> I[Recall = TP / (TP + FN)]

In Context

Typically used together with precision, F1-score, and ROC-AUC
Related to: Precision, Sensitivity, Specificity, F1-score
Example use cases: Cancer diagnosis, Spam detection, Fraud detection

Quelle: AI Generated