Multi-objective evolutionary feature selection for ensemble learning with random forests in time series forecasting

Espinosa, Raquel; Sánchez Carpena, Gracia; Palma Méndez, José Tomás; Jiménez Barrionuevo, Fernando

Publication:
Multi-objective evolutionary feature selection for ensemble learning with random forests in time series forecasting

dc.contributor.author	Espinosa, Raquel
dc.contributor.author	Sánchez Carpena, Gracia
dc.contributor.author	Palma Méndez, José Tomás
dc.contributor.author	Jiménez Barrionuevo, Fernando
dc.contributor.department	Ingeniería de la Información y las Comunicaciones
dc.contributor.other	Facultades de la UMU::Facultad de Informática
dc.date.accessioned	2025-12-17T12:25:23Z
dc.date.available	2025-12-17T12:25:23Z
dc.date.copyright	© 2025 The Authors
dc.date.issued	2025-11-10
dc.description.abstract	Time series forecasting is fundamental in numerous domains, including finance, healthcare, energy, and environmental monitoring. However, the high dimensionality of feature spaces can lead to overfitting and reduced interpretability, making feature selection a crucial preprocessing step. This paper proposes a multiobjective evolutionary algorithm for feature selection in time series forecasting, designed to enhance predictive accuracy while improving generalization. The method partitions the dataset, associating each partition with an objective function in the optimization process. By independently selecting relevant feature subsets, it generates a Pareto front of Random Forest models, each trained on a distinct subset of features. These models are then aggregated into a stacking-based ensemble framework, effectively balancing feature relevance and diversity. Additionally, we introduce a feature importance measure based on selection frequency in the non-dominated solutions of the optimization process. To validate our approach, we conduct experiments on real-world forecasting tasks, including air quality prediction in southeastern Spain and Italy and oil temperature forecasting in industrial applications. We also evaluate performance on synthetic datasets of increasing complexity, systematically varying instances, features, seasonality, noise, and trends. The proposed method is compared against conventional Random Forest, a wrapper-based feature selection method with a multiobjective evolutionary search strategy, and several state-of-the-art embedded feature selection techniques for time series forecasting. The results demonstrate that our approach significantly improves forecasting accuracy while mitigating overfitting. By integrating multi-objetive evolutionary optimization, random forest, ensemble learning, and a novel feature importance measure, our method offers a robust, interpretable, and effective feature selection for time series forecasting applications.
dc.format	application/pdf
dc.format.extent	29
dc.identifier.citation	Swarm and Evolutionary Computation, 2025, Vol. 99 : 102211
dc.identifier.doi	https://doi.org/10.1016/j.swevo.2025.102211
dc.identifier.eissn	2210-6510
dc.identifier.issn	2210-6502
dc.identifier.uri	http://hdl.handle.net/10201/181009
dc.language	eng
dc.publisher	Elsevier
dc.relation	This paper is funded by the CALM-COVID19 project (Ref: PID2022-136306OB-I00), grant funded by Spanish Ministry of Science and Innovation and the Spanish Agency for Research .
dc.relation.publisherversion	https://www.sciencedirect.com/science/article/pii/S2210650225003682
dc.rights	Attribution-NonCommercial-NoDerivatives 4.0 International	*
dc.rights.accessRights	info:eu-repo/semantics/openAccess
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/4.0/	*
dc.subject	Time series forecasting
dc.subject	Feature selection
dc.subject	Multi objetive evolutionary algorithms
dc.subject	Random forest
dc.subject	Ensemble learning
dc.subject	Stacking
dc.subject.ods	No relacionado con ningún objetivo de desarrollo sostenible
dc.title	Multi-objective evolutionary feature selection for ensemble learning with random forests in time series forecasting
dc.type	info:eu-repo/semantics/article
dc.type.version	info:eu-repo/semantics/publishedVersion
dspace.entity.type	Publication	es
relation.isAuthorOfPublication	02c0a87a-b9b1-419f-8464-ff56001af67e
relation.isAuthorOfPublication	490d158d-e40d-4fdf-99f0-912bd4aa5a4e
relation.isAuthorOfPublication	47706328-5460-433a-b86f-dcbcc9841c53
relation.isAuthorOfPublication.latestForDiscovery	02c0a87a-b9b1-419f-8464-ff56001af67e