Forecasting earning of VLCC tankers using artificial neural networks
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Shipping companies consistently want to minimize losses and maximize profits by accurately predicting the direction and magnitude of fluctuations in maritime situations. However, the determinants of maritime markets are diverse and volatile, and the decision mechanism is complex. Accurately predicting the direction and magnitude of fluctuations remains a difficult challenge. This study was conducted to evaluate the accuracy of multi-step-ahead forecasting of VLCC tanker markets by using an artificial neural network (ANN) training algorithm with the Levenberg-Marquardt and Bayesian regularization algorithms. The advanced time for forecasting was divided into one, three, six, nine, 12, and 15 months. The ANN predictions were conducted on the earnings for VLCC markets, and the datasets of the variables used in the forecast were 204 monthly time-series data from January 2000 to December 2016.
Abstract
Shipping companies consistently want to minimize losses and maximize profits by accurately predicting the direction and magnitude of fluctuations in maritime situations. However, the determinants of maritime markets are diverse and volatile, and the decision mechanism is complex. Accurately predicting the direction and magnitude of fluctuations remains a difficult challenge. This study was conducted to evaluate the accuracy of multi-step-ahead forecasting of VLCC tanker markets by using an artificial neural network (ANN) training algorithm with the Levenberg-Marquardt and Bayesian regularization algorithms. The advanced time for forecasting was divided into one, three, six, nine, 12, and 15 months. The ANN predictions were conducted on the earnings for VLCC markets, and the datasets of the variables used in the forecast were 204 monthly time-series data from January 2000 to December 2016.
참고문헌 (15)
- "The International Energy Agency (IEA)"[URL]
- "Clarksons Research Services"[URL]
- D. Hawdon, "Tanker freight rates in the short and long run", Applied Economics, 10(3), pp.203~217 (1978)
- A. H. Alizadeh, "Trading strategies in the market for tankers", Maritime Policy and Management, 33(2), pp.119~140 (2006)
- K. L. Du, "Neural Networks and Statistical Learning" (2014), Springer
- D. F. Shanno, "Recent advances in numerical techniques for large scale optimization, Neural networks for control" (1990), MIT Press
- L. E. Scales, "Introduction to Non-Linear Optimization", pp.110~136 (1985), Springer-Verlag
- "Neural Network Design" (2014)[URL]
- A. N. Tikhonov, "On the solution of ill-posed problems and the regularization method", Dokl. Acad. Nauk USSR, 151(3), pp.501~504 (1963)
- M. Beenstock, "An econometric model of the world tanker market", Journal of Transport Economics and Policy, 23(2), pp.263~280 (1989)
- M. G. Kavussanos, "Time varying risks among segments of the tanker freight markets", Maritime Economics and Logistics, 5(3), pp.227~250 (2003)
- J. Li, "Forecasting tanker freight rate using neural networks", Maritime Policy and Management, 24(1), pp.9~30 (1997)
- P. Eslami, "Predicting tanker freight rates using parsimonious variables and a hybrid artificial neural network with an adaptive genetic algorithm", Maritime Economics & Logistics, 1(13) (2016)
- D. V. Lyridis, "Forecasting tanker market using artificial neural network", Maritime Economics and Logistics, 6(2), pp.93~108 (2004)
- A. Santos, "Forecasting period charter rates of VLCC tankers through neural networks : A comparison of alternative approaches", Maritime Economics & Logistics, 16(1), pp.72~91 (2013)