<ul><li>Imbalanced regression occurs when continuous target variables have skewed distributions, creating sparse regions that are difficult for machine learning models to predict accurately.</li><li>Existing approaches often rely on arbitrary thresholds to categorize samples as rare or frequent, ignoring the continuous nature of target distributions.</li><li>To address these limitations, the proposed approach called LDAO (Local Distribution-based Adaptive Oversampling) learns the global distribution structure by decomposing the dataset into a mixture of local distributions and models each distribution independently before merging them into a balanced training set.</li><li>In extensive evaluations, LDAO outperforms state-of-the-art oversampling methods on both frequent and rare target values, demonstrating its effectiveness for addressing the challenge of imbalanced regression.</li></ul>

Local distribution-based adaptive oversampling for imbalanced regression

Discover more