What the F-measure doesn't measure: Features, Flaws, Fallacies and Fixes

2015/03/22 by David Powers, Powers, David M. W. · 1 citation
Computer Science · #68Q32 #68T05 #91E45 #Computation (stat.CO) #Computation and Language (cs.CL) #D.2.8 #FOS: Computer and information sciences #I.2.6 #I.2.7 #I.4.6 #I.5.1 #Information Retrieval (cs.IR) #Information Retrieval and Search Behavior #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Mathematics, Computing, and Information Processing #Natural Language Processing Techniques #Neural and Evolutionary Computing (cs.NE)

paper · pdf · doi:10.48550/arxiv.1503.06410

openalex publication_date 2015/03/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The F-measure or F-score is one of the most commonly used single number measures in Information Retrieval, Natural Language Processing and Machine Learning, but it is based on a mistake, and the flawed assumptions render it unsuitable for use in most contexts! Fortunately, there are better alternatives.

Cited by

• Multi-Scale Deep Learning for Colon Histopathology: A Hybrid Graph-Transformer Approach

Related

• F*: An Interpretable Transformation of the F-measure
• A Note on Comparison of F-measures
• Confidence Intervals for the F1 Score: A Comparison of Four Methods
• More accurate tests for the statistical significance of result differences
• Good Classification Measures and How to Find Them