Planning for the future is difficult in maritime industry in the current pandemic due to active dynamic factors similar to several industries. Thus, the present study aimed to determine freight demand estimates based on the TEU-based monthly number of containers handled in Turkish ports by comparing the prediction accuracy and reliability of artificial neural network models with various algorithms using the "Exponential Smoothing" and "Box-Jenkins" time series methods. The monthly container volume handled in Turkish ports between January 2005 and December 2018 was employed in the study. ADF tests were calculated with "E-Views 5" software. However, several tests conducted in the study revealed that the 12-time delay artificial neural network model, which was developed with the original series, provided the highest accuracy. In the study, demand forecasts for the container volume that would be handled in Turkish ports were conducted for 2022 with the developed model, and a methodological approach was presented for forecast models in different maritime industry fields.
Keywords: Container, maritime commerce, artificial neural networks, time series, Turkey.