Forecasting tanker freight rate using neural networks
Jun Li, Michael G. Parsons · Maritime Policy & Management · 1997
Improvement in forecasting accuracy is a difficult task but critical for business success. This paper investigates the potential of neural networks for short- to long-term prediction of monthly tanker freight rates. Procedures are outlined for the development of the neural networks. The problem of under-training and over-training is addressed by controlling the number of iterations during the training process of neural networks. A comparative study of predictive performance between neural networks and ARMA time series models is conducted. Our evience shows that neural networks can significantly outperform time series models, especially for longer-term forecasting.