ClustEval clustering evaluation framework
The FPR relates the number of false positives to the total number of negative elements. This estimates a likelihood of an element being predicted positive, if it is negative. This measure is based on the pairwise approach to calculate TP,TN,FP and FN. $FPR = \frac{FP}{FP+TN}$ In the binary classification background we have two classes that we want to distinguish: positive and negative. In this scenario there are four possible outcomes: