{
  "slug": "f1-score",
  "term": "F1 score",
  "aliases": [
    "balanced F-score",
    "F1 measure"
  ],
  "definition": "F1 score is the harmonic mean of precision and recall for a specified positive class and decision threshold.",
  "note": "For binary predictions, F1 = 2TP / (2TP + FP + FN); true negatives do not enter this formula. If TP, FP and FN are all zero, it is undefined; report the software's zero-division convention. F1 is neither recall nor accuracy, and multiclass or multilabel results must state the averaging rule. [sklearn-f1] Separately averaged or median precision and recall do not generally reconstruct an averaged or median F1. [sklearn-metrics]",
  "limitations": [
    {
      "text": "A single F1 value does not state how many healthy drives trigger alerts or the operational cost of false alarms; retain precision, recall, prevalence and the counting unit.",
      "citationIds": [
        "sklearn-metrics"
      ]
    }
  ],
  "related": [
    "precision",
    "recall",
    "false-positive-rate",
    "class-prevalence",
    "average-precision",
    "temporal-validation"
  ],
  "citations": [
    {
      "id": "sklearn-f1",
      "title": "scikit-learn: f1_score, binary formula, averaging and zero-division conventions.",
      "url": "https://scikit-learn.org/stable/modules/generated/sklearn.metrics.f1_score.html",
      "accessed": "2026-10-14"
    },
    {
      "id": "sklearn-metrics",
      "title": "scikit-learn: precision, recall and F-measures; aggregation and metric denominators.",
      "url": "https://scikit-learn.org/stable/modules/model_evaluation.html#precision-recall-and-f-measures",
      "accessed": "2026-10-14"
    }
  ],
  "status": "shipping",
  "advantages": [],
  "supersedes": [],
  "supersededBy": [],
  "firstSeen": null,
  "lastSeen": null,
  "updated": "2026-10-14"
}