Hybrid approaches based on SARIMA and artificial neural networks for inspection time series forecasting

•The number of goods subject to inspection at Border Inspection Posts was modelled.•Novel hybrid forecasting approaches based on SARIMA and ANNs models were tested.•The novel approaches outperform the traditional hybrid approach and the single models.•This methodology can be a powerful tool for decision making at inspection facilities.

In this paper, the number of goods subject to inspection at European Border Inspections Post are predicted using a hybrid two-step procedure. A hybridization methodology based on integrating the data obtained from autoregressive integrated moving averages (SARIMA) model in the artificial neural network model (ANN) to predict the number of inspections is proposed. Several hybrid approaches are compared and the results indicate that the hybrid models outperform either of the models used separately. This methodology may become a powerful decision-making tool at other inspection facilities of international seaports or airports.

Graphical abstractFigure optionsDownload full-size imageDownload as PowerPoint slide