https://doi.org/10.1051/epjconf/201921406004
Binary classifier metrics for optimizing HEP event selection
CERN, Information Technology Department,
CH-1211 Geneva 23,
Switzerland
* e-mail: andrea.valassi@cern.ch
Published online: 17 September 2019
I discuss the choice of evaluation metrics for binary classifiers in High Energy Physics (HEP) event selection and I point out that the Area Under the ROC Curve (AUC) is of limited relevance in this context, after discussing its use in other domains. I propose new metrics based on Fisher information, which can be used for both the evaluation and training of HEP event selection algorithms in statistically limited measurements of a parameter.
© The Authors, published by EDP Sciences, 2019
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
