Notes on the H-measure of classifier performance
This provides incremental clarifications for researchers and practitioners using the H-measure in machine learning evaluation.
The paper addresses user queries about the H-measure, a classifier performance metric introduced in 2009 that incorporates application context without fixed misclassification costs, by clarifying its interpretation, weighting function choice, propriety, coherence, and relation to other work.
The H-measure is a classifier performance measure which takes into account the context of application without requiring a rigid value of relative misclassification costs to be set. Since its introduction in 2009 it has become widely adopted. This paper answers various queries which users have raised since its introduction, including questions about its interpretation, the choice of a weighting function, whether it is strictly proper, and its coherence, and relates the measure to other work.