# An Insight on Evaluation Metrics Under the Imbalanced Case of Anomaly Detection

arXiv: https://arxiv.org/abs/2607.22286 · HTML: https://mlsanity.com/paper/2607.22286/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 27 references that are in the map.
- First posted on arXiv 24 Jul 2026.

## Builds on (most cited first, 8 of 8)

- [SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation](https://mlsanity.com/paper/2207.14315/) (2022)
- [Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progress](https://mlsanity.com/paper/2009.13807/) (2020)
- [Common Limitations of Image Processing Metrics: A Picture Story](https://mlsanity.com/paper/2104.05642/) (2021)
- [Time Series Anomaly Detection for Cyber-Physical Systems via Neural System Identification and Bayesian Filtering](https://mlsanity.com/paper/2106.07992/) (2021)
- [Navigating the Metric Maze: A Taxonomy of Evaluation Metrics for Anomaly Detection in Time Series](https://mlsanity.com/paper/2303.01272/) (2023)
- [Balancing the Scales: A Comprehensive Study on Tackling Class Imbalance in Binary Classification](https://mlsanity.com/paper/2409.19751/) (2024)
- [Removing Geometric Bias in One-Class Anomaly Detection with Adaptive Feature Perturbation](https://mlsanity.com/paper/2503.05520/) (2025)
- [ASTER: Latent Pseudo-Anomaly Generation for Unsupervised Time-Series Anomaly Detection](https://mlsanity.com/paper/2604.13924/) (2026)

## Abstract (arXiv)

Anomaly detection is inherently characterised by severe class imbalance, making the interpretation of evaluation metrics challenging. Although metrics such as AUROC, AUPR, F1-score, and MCC are widely used, their values convey different meanings depending on the anomaly ratio. In this work, we analyse the behaviour of those four common anomaly detection metrics under varying levels of imbalance. We focus on the study of metric landscapes, visualisations that relate metric values to true positive and true negative rates, providing an intuitive view of metric preferences and stability. Our analysis offers practical guidance for interpreting and comparing anomaly detection results across datasets with different imbalance ratios.