F*: An Interpretable Transformation of the F-measure
This addresses a conceptual issue for researchers and practitioners using classification metrics, but it is incremental as it modifies an existing measure without new data or broad SOTA impact.
The paper tackles the lack of intuitive interpretation in the F-measure by proposing a simple transformation called F*, which provides an immediate practical interpretation.
The F-measure, also known as the F1-score, is widely used to assess the performance of classification algorithms. However, some researchers find it lacking in intuitive interpretation, questioning the appropriateness of combining two aspects of performance as conceptually distinct as precision and recall, and also questioning whether the harmonic mean is the best way to combine them. To ease this concern, we describe a simple transformation of the F-measure, which we call F* (F-star), which has an immediate practical interpretation.