Artificial neural networks in freight rate forecasting
- 22 Downloads
Reliable freight rate forecasts are essential to stimulate ocean transportation and ensure stakeholder benefits in a highly volatile shipping market. However, compared to traditional time-series approaches, there are few studies using artificial intelligence techniques (e.g. artificial neural networks, ANNs) to forecast shipping freight rates, and fewer still incorporating forward freight agreement (FFA) information for freight rate forecasts. The aim of this paper is to examine the ability of FFAs to improve forecasting accuracy. We use two different dynamic ANN models, NARNET and NARXNET, and we compare their performance for 1, 2, 3 and 6 months ahead. The accuracy of the forecasting models is evaluated with the use of mean squared error (MSE), based on actual secondary data including historical Baltic Panamax Index (BPI) data (available online), and primary data on Baltic forward assessment (BFA) collected from the Baltic Exchange. The experimental results show that, in general, NARXNET outperforms NARNET in all forecast horizons, revealing the importance of the information contained in FFAs in improving forecasting accuracy. Our findings provide better forecasts and insights into the future movements of freight markets and help rationalise chartering decisions.
KeywordsFreight rate forecasting ANN FFA Maritime risk Maritime transport
This research is sponsored by two EU H2020 MC RISE programmes (Grant Nos. ENRICH-612546 and GOLF-777742). The authors thank the anonymous reviewers and the Editor-in-Chief of MEL for their valuable comments, which have improved the quality of this paper.
- Bao, J., Pan, L. and Xie, Y. 2016 ‘A new BDI forecasting model based on support vector machine.’ 2016 IEEE information technology, networking, electronic and automation control conference information technology, networking, electronic and automation control conference, IEEE, 65–69.Google Scholar
- BPI. 2017. https://www.quandl.com/data/LLOYDS/BPI-Baltic-Panamax-Index. Accessed: 2 March 2017.
- Gavin, H.P. (2017) The Levenberg-Marquardt method for nonlinear least squares curve-fitting problems. http://people.duke.edu/~hpgavin/ce281/lm.pdf. Accessed: 5 August 2017.
- Hagan, M.T., Demuth, H.B., Beale, M.H. and De Jesus, O. 2014. Neural network design. 2nd ed. Available at: http://hagan.okstate.edu/NNDesign.pdf. Accessed 5 March 2017.
- Kasimati, E., and N. Veraros. 2017. Accuracy of forward freight agreements in forecasting future freight rates. Applied Economics 50: 1–14.Google Scholar
- Kavussanos, M.G. 1996. Comparisons of volatility in the dry-cargo ship sector: Spot versus time charters, and smaller versus larger vessels. Journal of Transport Economics and Policy 30 (1): 67–82.Google Scholar
- Kisi, O., and E. Uncuoglu. 2005. Comparison of three back-propagation training algorithms for two case studies. Indian Journal of Engineering and Materials Sciences 12: 434–442.Google Scholar
- Lourakis, M. 2005. A brief description of the levenberg-marquardt algorithm implemented by levmar. http://users.ics.forth.gr/~lourakis/levmar/levmar.pdf. Accessed: 18 August 2017.
- Montgomery, D.C., C.L. Jennings, and M. Kulahci. 2015. Introduction to time series analysis and forecasting, 2nd ed. NJ: Wiley.Google Scholar
- NN Toolbox. 2017. https://www.mathworks.com/products/neural-network.html. Accessed: 5 March 2017.
- Oancea, B., and S.K. Ciucu. 2013. Time series forecasting using neural networks. Challenges of the Knowledge Society 3: 1402–1408.Google Scholar
- Sapna, S. 2012. ‘Backpropagation Learning Algorithm Based on Levenberg Marquardt Algorithm’, The Fourth International Workshops on Computer Network & Communications, 26th to 28th October. Coimbatore.Google Scholar
- Tsioumas, V., and S. Papadimitriou. 2015. Chinese steel production and shipping freight markets: A causality analysis. International Journal of Business and Economic Development 3 (2): 116–124.Google Scholar
- Tsioumas, V., and S. Papadimitriou. 2016. The dynamic relationship between freight markets and commodity prices revealed. Maritime Economics and Logistics 20: 1–13.Google Scholar
- UNCTAD. 2016. Review of maritime transport 2016. http://unctad.org/en/PublicationsLibrary/rmt2016_en.pdf. Accessed: 2 March 2017.
- Veenstra, A.W., and P.H. Franses. 1997. A co-integration approach to forecasting freight rates in the dry bulk shipping sector. Transportation Research Part A: Policy and Practice 31 (6): 447–459.Google Scholar
- Visvikis, I. D. (2002) An econometric analysis of the forward freight market. http://openaccess.city.ac.uk/7596/. Accessed: 01 March 2017.
- Zhang, J., G. Zheng, and X. Zhao. 2014. Forecasting spot freight rates based on forward freight agreements and time charter contracts. Applied Economics 46 (29): 3639–3648.Google Scholar