Litcius/Paper detail

Hierarchical confusion matrix for classification performance evaluation

Kevin Riehl, Michael Neunteufel, Martin Hemberg

2023Journal of the Royal Statistical Society Series C (Applied Statistics)53 citationsDOIOpen Access PDF

Abstract

Abstract This study proposes the novel concept of hierarchical confusion matrix, opening the door for popular confusion-matrix-based (flat) evaluation measures from binary classification problems, while considering the peculiarities of hierarchical classification problems. The concept is developed to a generalised form and proven its applicability to all types of hierarchical classification problems including directed acyclic graphs, multi-path labelling, and non-mandatory leaf-node prediction. Finally, measures based on the novel confusion matrix are used for three real-world hierarchical classification applications and compared to established evaluation measures. The results, the conformity with important attributes of hierarchical classification schemes and its broad applicability justify its recommendation.

Topics & Concepts

Confusion matrixConfusionComputer scienceConformityMatrix (chemical analysis)Logical matrixNode (physics)Hierarchical database modelArtificial intelligenceClassification schemeData miningMachine learningEngineeringPsychologyGroup (periodic table)Materials sciencePsychoanalysisChemistryStructural engineeringComposite materialSocial psychologyOrganic chemistryText and Document Classification TechnologiesImbalanced Data Classification TechniquesRough Sets and Fuzzy Logic