# Beyond Imbalance Ratio: Data Characteristics as Critical Moderators of Oversampling Method Selection

arXiv: https://arxiv.org/abs/2604.04541 · HTML: https://mlsanity.com/paper/2604.04541/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 43 references that are in the map.
- First posted on arXiv 6 Apr 2026.

## Builds on (most cited first, 9 of 9)

- [OpenML: networked science in machine learning](https://mlsanity.com/paper/1407.7722/) (2014)
- [Should we really use post-hoc tests based on mean-ranks?](https://mlsanity.com/paper/1505.02288/) (2015)
- [Generative Adversarial Minority Oversampling](https://mlsanity.com/paper/1903.09730/) (2019)
- [Conditional Wasserstein GAN-based Oversampling of Tabular Data for Imbalanced Learning](https://mlsanity.com/paper/2008.09202/) (2020)
- [DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Data](https://mlsanity.com/paper/2105.02340/) (2021)
- [Radial-Based Undersampling for Imbalanced Data Classification](https://mlsanity.com/paper/1906.00452/) (2019)
- [Bayes Imbalance Impact Index: A Measure of Class Imbalanced Dataset for Classification Problem](https://mlsanity.com/paper/1901.10173/) (2019)
- [GK-SMOTE: A Hyperparameter-free Noise-Resilient Gaussian KDE-Based Oversampling Approach](https://mlsanity.com/paper/2509.11163/) (2025)
- [GAT-RWOS: Graph Attention-Guided Random Walk Oversampling for Imbalanced Data Classification](https://mlsanity.com/paper/2412.16394/) (2024)

## Abstract (arXiv)

The prevailing IR-threshold paradigm posits a positive correlation between imbalance ratio (IR) and oversampling effectiveness, yet this assumption remains empirically unsubstantiated through controlled experimentation. We conducted 12 controlled experiments (N > 100 dataset variants) that systematically manipulated IR while holding data characteristics (class separability, cluster structure) constant via algorithmic generation of Gaussian mixture datasets. Two additional validation experiments examined ceiling effects and metric-dependence. All methods were evaluated on 17 real-world datasets from OpenML. Upon controlling for confounding variables, IR exhibited a weak to moderate negative correlation with oversampling benefits. Class separability emerged as a substantially stronger moderator, accounting for significantly more variance in method effectiveness than IR alone. We propose a 'Context Matters' framework that integrates IR, class separability, and cluster structure to provide evidence-based selection criteria for practitioners.