English

Using theoretical ROC curves for analysing machine learning binary classifiers

Machine Learning 2019-09-24 v1 Computer Vision and Pattern Recognition Machine Learning

Abstract

Most binary classifiers work by processing the input to produce a scalar response and comparing it to a threshold value. The various measures of classifier performance assume, explicitly or implicitly, probability distributions PsP_s and PnP_n of the response belonging to either class, probability distributions for the cost of each type of misclassification, and compute a performance score from the expected cost. In machine learning, classifier responses are obtained experimentally and performance scores are computed directly from them, without any assumptions on PsP_s and PnP_n. Here, we argue that the omitted step of estimating theoretical distributions for PsP_s and PnP_n can be useful. In a biometric security example, we fit beta distributions to the responses of two classifiers, one based on logistic regression and one on ANNs, and use them to establish a categorisation into a small number of classes with different extremal behaviours at the ends of the ROC curves.

Keywords

Cite

@article{arxiv.1909.09816,
  title  = {Using theoretical ROC curves for analysing machine learning binary classifiers},
  author = {Luma Omar and Ioannis Ivrissimtzis},
  journal= {arXiv preprint arXiv:1909.09816},
  year   = {2019}
}

Comments

10 pages, 4 figures