Maximization of AUC and buffered AUC in binary classification

DOI10.1007/s10107-018-1312-2zbMath1421.90099OpenAlexW2844677341WikidataQ129580861 ScholiaQ129580861MaRDI QIDQ1739053

Stan Uryasev, Matthew Norton

Publication date: 24 April 2019

Published in: Mathematical Programming. Series A. Series B (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10107-018-1312-2

zbMATH Keywords

AUCconvex programminggeneralizationROC curvesupport vector machineconditional-value-at-riskbuffered probability of exceedancebuffered AUCclassification performance metric

Mathematics Subject Classification ID

Convex programming (90C25) Stochastic programming (90C15) Pattern recognition, speech recognition (68T10)

Related Items (16)

A distributionally robust area under curve maximization model ⋮ Gradients and subgradients of buffered failure probability ⋮ Ellipsoidal buffered area under the curve maximization model with variable selection in credit risk estimation ⋮ Minimizing buffered probability of exceedance by progressive hedging ⋮ Buffered-ranking intervals for virtual profit efficiency analysis ⋮ Goal scoring, coherent loss and applications to machine learning ⋮ A new method of reliability optimization in the classical problem statement ⋮ Buffered and reduced multidimensional distribution functions and their application in optimization ⋮ Cash flow matching with risks controlled by buffered probability of exceedance and conditional value-at-risk ⋮ Application of buffered probability of exceedance in reliability optimization problems ⋮ Buffered Probability of Exceedance: Mathematical Properties and Optimization ⋮ Calculating CVaR and bPOE for common probability distributions with application to portfolio optimization and density estimation ⋮ Estimation and asymptotics for buffered probability of exceedance ⋮ Derivatives and subderivatives of buffered probability of exceedance ⋮ Unnamed Item ⋮ Solving Nonsmooth and Nonconvex Compound Stochastic Programs with Applications to Risk Measure Minimization

Uses Software

• UCI-ml
• Scikit

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A classification problem of credit risk rating investigated and solved by optimisation of the ROC curve
• Estimation and asymptotics for buffered probability of exceedance
• Support-vector networks
• Measuring the Accuracy of Diagnostic Systems
• Buffered Probability of Exceedance: Mathematical Properties and Optimization
• 10.1162/153244302760200704

This page was built for publication: Maximization of AUC and buffered AUC in binary classification