Predictive classification in GeneSpring GX is accompanied by class belongingness measure which corresponds from 0 to 1. The Lorenz Curve is used to visualize the ordering of this measure for a particular class. The items are ordered with the predicted class being sorted from 1 to 0 and the other classes being sorted from 0 to 1 for each class. The Lorenz curve plots the fraction of items of a particular class encountered (Y-axis) against the total item count (X-axis).
The main advantage of this curve is that in situations where the overall classification accuracy is not very high, one may still be able to correctly classify a certain fraction of the items in a class with very few false positives. The Lorenz curve also allows visual identification of this fraction (essentially the point where the red line starts departing substantially from the steady slope line to Y=1).