机器学习-分类度量(classification metric)常用评价指标

  1. 评判指标存在的目的
  2. 应用场景
  3. 混淆矩阵
  4. accuracy =(TP+TN)/(TP+TN+FP+FN)
  5. precision =TP/(TP+FP)
  6. recall 召回率=真阳性率(True Positive Rate,TPR)=灵敏度(Sensitivity)=(TP/TP+FN)
  7. P-R曲线=precision recall curve
  8. 真阴性率(True Negative Rate,TNR),特异度(Specificity)=TN/(TN+FP)
  9. F1-Score=2precisionrecall/(precision+recall)
  10. 假阴性率(False Negatice Rate,FNR)=1 - 灵敏度(Sensitivity)=FN/(TP+FN)
  11. 假阳性率(False Positice Rate,FPR)= 1 - 特异度(Specificity)=FP/(FP+TN)
  12. ROC曲线=接收者操作特征曲线(receiver operating characteristic curve)
  13. 曲线下面积(Area Under Curve)
  14. 多分类问题
    机器学习-分类度量(classification metric)常用评价指标