Soft precision and recall
Pasi Fränti, Radu Mariescu-Istodor
Abstract
Precision and recall are classical measures used in machine learning. However, they are based on exact matching. This results in binary classification where the predicted item is either a true or false positive despite inexact matching is often preferred in pattern recognition. To address this problem, we introduce soft variants of precision and recall based on application-specific similarity measure. 2022 Elsevier Ltd. All rights reserved.
Topics & Concepts
RecallPrecision and recallMatching (statistics)Artificial intelligenceComputer scienceSimilarity (geometry)Pattern recognition (psychology)Binary numberMeasure (data warehouse)Binary classificationMachine learningMathematicsData miningStatisticsSupport vector machineArithmeticPsychologyCognitive psychologyImage (mathematics)Music and Audio ProcessingTime Series Analysis and ForecastingAnomaly Detection Techniques and Applications