评估指标：ROC，AUC，Precision、Recall、F1-score

一、ROC，AUC

ROC（Receiver Operating Characteristic）曲线和AUC常被用来评价一个二值分类器（binary classifier）的优劣 。

ROC曲线一般的横轴是FPR，纵轴是FPR。AUC为曲线下面的面积，作为评估指标，AUC值越大，说明模型越好。如下图：

 

二、Precision、Recall、F1-score

true positive (TP)

eqv. with hit

true negative (TN)

eqv. with correct rejection

false positive (FP)

eqv. with false alarm, Type I error

false negative (FN)

eqv. with miss, Type II error

---

sensitivity or true positive rate (TPR)

eqv. with hit rate, recall

specificity (SPC) or true negative rate (TNR)

precision or positive predictive value (PPV)

negative predictive value (NPV)

fall-out or false positive rate (FPR)

false discovery rate (FDR)

miss rate or false negative rate (FNR)

---

accuracy (ACC)

F1 score

is the harmonic mean of precision and sensitivity

Matthews correlation coefficient (MCC)

Informedness = Sensitivity + Specificity - 1
Markedness = Precision + NPV - 1

中文解释