The Receiver Operating Characteristic (ROC) curve is a plot used to evaluate the performance of binary classifiers on which a decision threshold can be set. For example, if a model outputs a probability that a sample belongs to the "positive" class, a typical decision threshold is 0.5, but other values can be set. While varying the decision threshold, a pair of metrics is computed: the False Positive Rate, and the True Positive Rate. These are defined as such: FPR = FP/(FP+TN), TPR = TP/(TP+FN), where FP is the number of false positives, TN is the number of true negatives, TP is the number of true positives, and FN is the number of false negatives. A good model has high TPR values while keeping FPR values low, thus the area under the ROC curve (typically referred to as AUC) is often used to assess the quality of a model.