# Robust performance metrics for imbalanced classification problems

arXiv: https://arxiv.org/abs/2404.07661 · HTML: https://mlsanity.com/paper/2404.07661/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 29 references that are in the map.
- First posted on arXiv 11 Apr 2024.

## Builds on (most cited first, 3 of 3)

- [A systematic study of the class imbalance problem in convolutional neural networks](https://mlsanity.com/paper/1710.05381/) (2017)
- [Binary Classification with Karmic, Threshold-Quasi-Concave Metrics](https://mlsanity.com/paper/1806.00640/) (2018)
- [Optimal Binary Classification Beyond Accuracy](https://mlsanity.com/paper/2107.01777/) (2021)

## Built on by (most cited first, 1 of 1)

- [Machine Learning-Driven Predictive Resource Management in Complex Science Workflows](https://mlsanity.com/paper/2509.11512/) (2025)

## Abstract (arXiv)

We show that established performance metrics in binary classification, such as Matthews' correlation coefficient (MCC), Cohen's kappa, the F-score or the Jaccard similarity coefficient are not robust to class imbalance in the sense that if the proportion of the minority class tends to 0, the true positive rate (TPR) of the Bayes classifier under these metrics tends to 0 as well. Thus, in imbalanced classification problems, these metrics favour classifiers which ignore the minority class. To alleviate this issue we introduce robustified modifications of the MCC, of Cohen's kappa and of the F-score with an additional tuning parameter which allows to adapt the amount of robustness against class imbalance. As theoretical guarantee we show that the Bayes-optimal classifier for these robustified performance metrics, when expressed in terms of the density ratio f1/f0 of the class-conditional densities fi, has a threshold parameter which is upper-bounded in terms of the tuning parameters. Therefore, even in strongly imbalanced settings, the TPR associated to this classifier will be bounded away from 0. We numerically illustrate the behaviour of the various performance metrics and the effect of the tuning parameters in simulations as well as on a credit default data set. We also discuss connections to the receiver operating characteristic and precision-recall curves, which provide an alternative perspective on the proposed notion of robustness, and give recommendations on how to combine their usage with performance metrics.