Containerization is a critical component for Thailand's economics. However, forecasts of container growth and development of Bangkok Port, the main port of Thailand, have been scant and the findings are divergence. Moreover, the existing literature emphasizes only two forecasting methods, namely time series and regression analysis. The aim of this paper is to explore the use of neural network for predicting future container throughput at Bangkok Port. The use of neural network is evident as a forecasting method for business firms and government offices but absent in predicting container throughput. Factors affecting cargo throughput at Bangkok Port are identified and entered into the neural network forecasting model that generates a projection of cargo throughput. Then the results are measured by root mean squared error (RMSE) and mean absolute error (MAE). Based on the results, this research provides a discussion on the application of neural network for forecasting container throughput.
An application of neural networks for forecasting container throughput at Bangkok Port
2010
5 Seiten, 2 Bilder, 2 Tabellen, 46 Quellen
(nicht paginiert)
Conference paper
Storage medium
English
neuronales Netz , Vorhersage , Container (Transportbehälter) , Hafen , Zeitreihenanalyse , Regressionsanalyse , Statistik , Genauigkeit , Regierung , Unternehmen , Transportsystem , Import , Export , Handel , Literatur , Klassifizierung , Vorhersagemodell , Korrelationskoeffizient , Planung , Investition , Untersuchungsmethode
Application of Spreadsheet to Forecasting Port Throughput
British Library Online Contents | 2005
|World container port throughput follows lognormal distribution
Taylor & Francis Verlag | 2010
|World container port throughput follows lognormal distribution
Online Contents | 2010
|Taylor & Francis Verlag | 2016
|Forecasting container port volume: implications for dredging
Springer Verlag | 2017
|