163973 20251113160753.0 doi 10.1016/j.eswa.2025.129822 sideral 146094 ART-2026-146094 eng Beltran, Adelaida Ojeda Multivariate integration of time series with ML for corn price forecasting in Colombia 2026 The volatility of corn prices poses a significant challenge for both producers and policymakers. This study proposes a hybrid model that combines Extreme Gradient Boosting (XGBoost) and Light Gradient Boosting Machine (LightGBM), optimized through Particle Swarm Optimization with Cuckoo Search (PSO-CS), for accurate corn price forecasting. The approach integrates multivariate time series data, including local prices from the Atlántico market and international futures prices from the Chicago Board of Trade (CBOT). Empirical Mode Decomposition (EMD) is applied to enhance signal clarity and improve model performance. Model performance is assessed through sensitivity analysis and statistical comparison using the Diebold-Mariano (DM) test. The results demonstrate that the proposed ensemble outperforms both individual models and neural network combinations, achieving a Mean Absolute Percentage Error (MAPE) of 2.06. Access copy available to the general public Unrestricted info:eu-repo/grantAgreement/ES/DGA/T59-23R info:eu-repo/semantics/openAccess All rights reserved http://www.europeana.eu/rights/rr-f/ info:eu-repo/semantics/article info:eu-repo/semantics/acceptedVersion Suaza-Medina, Mario E. Universidad de Zaragoza (orcid)0000-0002-2112-3478 Zarazaga-Soria, F. Javier Universidad de Zaragoza (orcid)0000-0002-6557-2494 De-La-Hoz-Franco, Emiro Escorcia-Gutierrez, José 5007 570 Universidad de Zaragoza Dpto. Informát.Ingenie.Sistms. Área Lenguajes y Sistemas Inf. 299, Part A (2026), 129822 [23 pp.] Expert syst. appl. Expert Systems with Applications 0957-4174 1958760 http://zaguan.unizar.es/record/163973/files/texto_completo.pdf Postprint 3023742 http://zaguan.unizar.es/record/163973/files/texto_completo.jpg?subformat=icon icon Postprint oai:zaguan.unizar.es:163973 articulos driver 2025-11-13-14:58:51 ARTICLE