Histogram Approaches for Imbalanced Data Streams Regression

TL;DR

This paper introduces histogram-based sampling methods for imbalanced regression in data streams, enabling dynamic detection and prioritization of rare instances to improve prediction accuracy in evolving environments.

Contribution

It presents novel histogram-based undersampling and oversampling techniques that overcome previous assumptions, enhancing rare case detection in online imbalanced regression tasks.

Findings

HistUS and HistOS improve rare-case prediction accuracy.

The methods outperform baseline models and are competitive with Chebyshev-based approaches.

They effectively detect rare instances across arbitrary regions of the distribution.

Abstract

Imbalanced domains pose a significant challenge in real-world predictive analytics, particularly in the context of regression. While existing research has primarily focused on batch learning from static datasets, limited attention has been given to imbalanced regression in online learning scenarios. Intending to address this gap, in prior work, we proposed sampling strategies based on Chebyshevs inequality as the first methodologies designed explicitly for data streams. However, these approaches operated under the restrictive assumption that rare instances exclusively reside at distribution extremes. This study introduces histogram-based sampling strategies to overcome this constraint, proposing flexible solutions for imbalanced regression in evolving data streams. The proposed techniques -- Histogram-based Undersampling (HistUS) and Histogram-based Oversampling (HistOS) -- employ incremental online histograms to dynamically detect and prioritize rare instances across arbitrary regions of the target distribution to improve predictions in the rare cases. Comprehensive experiments on synthetic and real-world benchmarks demonstrate that HistUS and HistOS substantially improve rare-case prediction accuracy, outperforming baseline models while maintaining competitiveness with Chebyshev-based approaches.