Table A1 Confusion matrix and... | Emerald Publishing

Table A1

Confusion matrix and performance metrics

		Prediction
		Positive	Negative
Actual	Positive	True positive (TP)	False negative (FN)
Actual	Negative	False positive (FP)	True negative (TN)
TPR	True Positive Rate (TPR): the proportion of correctly predicted positive cases to the actual positive cases. An ideal result is to get a TPR of 1		$\frac{T P}{T P + F N}$
FPR	False Positive Rate (FPR): the proportion of wrongly predicted positive cases to the actual negative cases. An ideal result is to get an FPR of 0		$\frac{F P}{F P + T N}$
AUROC	A ROC curve is a plot that shows trade-offs between the TPR and FPR values. AUROC measures the area under the curve within a range between 0 and 1. A closer to 1 indicates better model performance

		Prediction
		Positive	Negative
Actual	Positive	True positive (TP)	False negative (FN)
Actual	Negative	False positive (FP)	True negative (TN)
TPR	True Positive Rate (TPR): the proportion of correctly predicted positive cases to the actual positive cases. An ideal result is to get a TPR of 1		$\frac{T P}{T P + F N}$
FPR	False Positive Rate (FPR): the proportion of wrongly predicted positive cases to the actual negative cases. An ideal result is to get an FPR of 0		$\frac{F P}{F P + T N}$
AUROC	A ROC curve is a plot that shows trade-offs between the TPR and FPR values. AUROC measures the area under the curve within a range between 0 and 1. A closer to 1 indicates better model performance

Source(s): Author’s own work