Table 2.

Definition of performance metrics

Performance metrices	Definition/explanation
Accuracy	$\frac{\text{True}\text{positive}(\text{TP})+\text{True}\text{negative}(\text{TN})}{\text{True}\text{positive}(\text{TP})+\text{True}\text{negative}(\text{TN})+\text{False}\text{positive}(\text{FP})+\text{False}\text{negative}(\text{FN})}$
Precision	$\frac{\text{TP}}{\text{TP}+\text{FP}}$
Recall (TP rate)	$\frac{\text{TP}}{\text{TP}+\text{FN}}$
F1-score	$\frac{\text{TP}\cdot \text{TP}}{\text{TP}+\text{TP}+\text{FP}+\text{FN}}$
Support	The number of actual occurrences of a class in the provided data set
FP rate	$\frac{\text{FP}}{\text{FP}+\text{TN}}$
Area under the curve (AUC)	AUC is an important feature of the ROC curve that measures the ability of a classifier to distinguish between classes. The greater the AUC, the better the model’s performance
ROC	An ROC, or ROC curve, is a graphical representation of a binary classifier
Macro average	All classes equally contribute to the final averaged metric
Weighted avg.	The weight of each class’s contribution to the average