RT journal article
T1 A freight inspection volume forecasting approach using an aggregation/disaggregation procedure, machine learning and ensemble models
A1 Ruiz Águilar, Juan Jesús
A1 Urda, Daniel
A1 Moscoso López, José Antonio
A1 González Enrique, Francisco Javier
A1 Turias Domínguez, Ignacio José
A2 Ingeniería Industrial e Ingeniería Civil
A2 Ingeniería Informática
K1 Machine learning
K1 Ensembles
K1 Artificial neural networks
K1 Bayesian regularization
K1 Aggregation/disaggregation
K1 Time series inspection
AB Machine learning methods are a powerful tool to detect workload peaks and congestion in goods inspec- tion facilities of seaports. In this paper, a time series data of freight inspection volume at the Border Inspections Posts in the Port of Algeciras Bay was used to construct 4 datasets based on different sizes of autoregressive window and several machine learning and ensemble models were used to aid decision- making in the inspection process. Moreover, an aggregation/disaggregation procedure to make predictions was proposed and compared to two different prediction horizons: daily ( t + 1 ) and weekly ( t + 7 ) pre- dictions. In general, results showed that neural networks performed better than any other model inde- pendently of the size of the autoregressive window. The result obtained by a weighted average ensemble model was better and statistically significant than any other model. Moreover, the proposed aggrega- tion/disaggregation procedure provided better performance results and more robust in terms of variance than considering daily or weekly predictions.
PB Elsevier
SN 1872-8286
YR 2020
FD 2020
LK http://hdl.handle.net/10498/35202
UL http://hdl.handle.net/10498/35202
LA eng
DS Repositorio Institucional de la Universidad de Cádiz
RD 07-nov-2026