Oversampling Techniques for Imbalanced Data in Regression

This paper introduces innovative oversampling techniques specifically designed to address the challenges of imbalanced data in regression tasks, which are often overlooked in favor of classification problems. The study identifies the unique issues associated with skewed distributions and high variance in minority data points that can adversely affect the performance of regression models.

The proposed techniques are rigorously tested against various benchmarks, demonstrating significant improvements in the accuracy and reliability of regression models trained on imbalanced datasets. This research provides valuable insights for practitioners and researchers in fields where regression tasks are common, ensuring that these models can better handle real-world data. The methods presented have been validated through extensive experimentation and are poised to make a substantial impact on the field of machine learning.

Recommended citation: Belhaouari, S. B., Islam, A., Kassoul, K., Al-Fuqaha, A., & Bouzerdoum, A. (2024). "Oversampling Techniques for Imbalanced Data in Regression." Expert Systems with Applications, 252, 124118. https://doi.org/10.1016/j.eswa.2024.124118
Download Paper | Download Slides