Time series forecasting of domestic shipping market: comparison of SARIMAX, ANN-based models and SARIMAX-ANN hybrid model

Seaborne transport forecasting has attracted substantial interest over the years because of providing a useful policy tool for decision-makers. Although various methods have been widely studied, there is still broad debate on accurate models and preprocessing. The current paper aims to point out these issues, as well establish model domestic cargo volumes using SARIMAX, MLP, LSTM NARX SARIMAX-ANN hybrid models. Based Turkey, findings suggest that SARIMA-MLP can be considered an appropriate alternative, at least time series shipping. Pre-processed data provides significant improvement those obtained with unpreprocessed data, accuracy found significantly boosted Fourier term decomposition. results indicate SARIMAX-MLP, mean absolute percentage error (MAPE) 4.81, outperforms closest MAPE 6.14 decomposition 6.52. Findings implications shipping policymakers plan infrastructure development, shipowners in accurately formulating demand.