On the Noise Resilience of Ranking Measures

• Published in: Neural Information Processing Vol. 9948; pp. 47 - 55
• Main Author: Berrar, Daniel
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2016; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: AUC; Classification; H-measure; Noise; Precision-recall curve; Ranking; Robustness; ROC curve; taKS

Performance measures play a pivotal role in the evaluation and selection of machine learning models for a wide range of applications. Using both synthetic and real-world data sets, we investigated the resilience to noise of various ranking measures. Our experiments revealed that the area under the R...