Imbalanced regression using regressor-classifier ensembles
Journal article, 2023

We present an extension to the federated ensemble regression using classification algorithm, an ensemble learning algorithm for regression problems which leverages the distribution of the samples in a learning set to achieve improved performance. We evaluated the extension using four classifiers and four regressors, two discretizers, and 119 responses from a wide variety of datasets in different domains. Additionally, we compared our algorithm to two resampling methods aimed at addressing imbalanced datasets. Our results show that the proposed extension is highly unlikely to perform worse than the base case, and on average outperforms the two resampling methods with significant differences in performance.

Imbalanced data

Ensemble regression

Machine learning

Author

Oghenejokpeme I. Orhobor

University of Cambridge

Nastasiya F. Grinberg

National Institute of Agricultural Botany

University of Cambridge

Larisa N. Soldatova

University of London

Ross King

Alan Turing Institute

University of Cambridge

Chalmers, Life Sciences, Systems and Synthetic Biology

Machine Learning

0885-6125 (ISSN) 1573-0565 (eISSN)

Vol. 112 4 1365-1387

Subject Categories

Computer Science

DOI

10.1007/s10994-022-06199-4

More information

Latest update

10/6/2023