Journal of Korean Society for Quality Management (품질경영학회지)

Korean Society for Quality Management (한국품질경영학회)
권호 표지
DOI QR코드

DOI QR Code

Prediction of Baltic Dry Index by Applications of Long Short-Term Memory

Long Short-Term Memory를 활용한 건화물운임지수 예측

  • HAN, Minsoo (Department of Shipping Management, Postgraduate School of Korea Maritime and Ocean University) ;
  • YU, Song-Jin (Department of Shipping Management, Korea Maritime and Ocean University)
  • 한민수 (한국해양대학교 대학원 해운경영학과) ;
  • 유성진 (한국해양대학교 해운경영학부)
  • Received : 2019.05.05
  • Accepted : 2019.06.17
  • Published : 2019.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

Purpose: The purpose of this study is to overcome limitations of conventional studies that to predict Baltic Dry Index (BDI). The study proposed applications of Artificial Neural Network (ANN) named Long Short-Term Memory (LSTM) to predict BDI. Methods: The BDI time-series prediction was carried out through eight variables related to the dry bulk market. The prediction was conducted in two steps. First, identifying the goodness of fitness for the BDI time-series of specific ANN models and determining the network structures to be used in the next step. While using ANN's generalization capability, the structures determined in the previous steps were used in the empirical prediction step, and the sliding-window method was applied to make a daily (one-day ahead) prediction. Results: At the empirical prediction step, it was possible to predict variable y(BDI time series) at point of time t by 8 variables (related to the dry bulk market) of x at point of time (t-1). LSTM, known to be good at learning over a long period of time, showed the best performance with higher predictive accuracy compared to Multi-Layer Perceptron (MLP) and Recurrent Neural Network (RNN). Conclusion: Applying this study to real business would require long-term predictions by applying more detailed forecasting techniques. I hope that the research can provide a point of reference in the dry bulk market, and furthermore in the decision-making and investment in the future of the shipping business as a whole.

Keywords

References

  1. Scarsi, Roberta. 2007. "The Bulk Shipping Business: Market Cycles and Shipowners' Biases." Maritime Policy & Management 34(6):577-590. https://doi.org/10.1080/03088830701695305
  2. Chiste, Claudio, and Gary Van Vuuren. 2014. "Investigating the Cyclical Behavior of the Dry Bulk Shipping Market." Maritime Policy & Management 41(1):1-19. https://doi.org/10.1080/03088839.2013.780216
  3. Courbariaux, Matthieu, et al. 2016. "Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1." arXiv, preprint arXiv:1602.02830:1-11.
  4. Cullinane, K. P. B., K. J. Mason, and M. Cape. 1999. "A Comparison of Models for Forecasting the Baltic Freight Index: Box-Jenkins Revisited." International Journal of Maritime Economics 1(2):15-39. https://doi.org/10.1057/ijme.1999.10
  5. Elman, Jeffrey L. 1990. "Finding Structure in Time." Cognitive Science 14(2):179-211. https://doi.org/10.1207/s15516709cog1402_1
  6. Fan, Yong Hui, Yu Wei Xing, and Hua Long Yang. 2014. "Prediction of Baltic Capesize Freight Index Based on GARCH Model." In Applied Mechanics and Materials 488:1494-1497. https://doi.org/10.4028/www.scientific.net/AMM.488-489.1494
  7. Geman, Hélyette, and William O. Smith. 2012. "Shipping Markets and Freight Rates: An Analysis of the Baltic Dry Index." Journal of Alternative Investments 15(1):98-109.
  8. HAN, Minsoo. 2019. "Prediction of Baltic Dry Index by Applications of Long Short-Term Memory Recurrent Neural Network Architectures." M.S. thesis., Korea Maritime and Ocean University.
  9. Hochreiter, Sepp, and Jurgen Schmidhuber. 1997. "Long short-term memory." Neural Computation, 9(8):1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  10. Hochreiter, Sepp, et al. 2001. "Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-term Dependencies." 1-15.
  11. Jordan, Michael I. 1997. "Serial Order: A Parallel Distributed Processing Approach." In Advances in Psychology 121:471-495. https://doi.org/10.1016/S0166-4115(97)80111-2
  12. Kavussanos, Manolis G., and Amir H. Alizadeh-M. 2001. "Seasonality Patterns in Dry Bulk Shipping Spot and Time Charter Freight Rates." Transportation Research Part E: Logistics and Transportation Review 37(6):443-467. https://doi.org/10.1016/S1366-5545(01)00004-7
  13. Kavussanos, Manolis G., and Amir H. Alizadeh-M. 2002. "Seasonality Patterns in Tanker Spot Freight Rate Markets." Economic Modelling 19(5):747-782. https://doi.org/10.1016/S0264-9993(01)00078-5
  14. Leonov, Yordan, and Ventsislav Nikolov. 2012. "A Wavelet and Neural Network Model for the Prediction of Dry Bulk Shipping Indices." Maritime Economics & Logistics 14(3):319-333. https://doi.org/10.1057/mel.2012.10
  15. Li, Jun, and Michael G. Parsons. 1997. "Forecasting Tanker Freight Rate using Neural Networks." Maritime Policy & Management 24(1):9-30. https://doi.org/10.1080/03088839700000053
  16. Lin, Faqin, and Nicholas CS Sim. 2013. "Trade, Income and the Baltic Dry Index." European Economic Review, 59:1-18. https://doi.org/10.1016/j.euroecorev.2012.12.004
  17. Lyridis, D. V., et al. 2004. "Forecasting Tanker Market using Artificial Neural Networks." Maritime Economics & Logistics 6(2):93-108. https://doi.org/10.1057/palgrave.mel.9100097
  18. Papailias, Fotis, Dimitrios D. Thomakos, and Jiadong Liu. 2017. "The Baltic Dry Index: cyclicalities, forecasting and hedging strategies." Empirical Economics 52(1):255-282. https://doi.org/10.1007/s00181-016-1081-9
  19. Signal Trading Group. 2011(revised in 2012). Bakshi, Gurdip, George Panayotov, and Georgios Skoulakis. "The Baltic Dry Index as a Predictor of Global Stock Rreturns, Commodity Returns, and Global Economic Activity." Accessed December 18. www.signaltradinggroup.com/wp-content/WhitePapers/Baltic Bakshi, Gurdip S. and Panayotov, George and Skoulakis, Georgios, The Baltic Dry Index as a Predictor of Global Stock Returns, Commodity Returns, and Global Economic Activity (January 26, 2011). AFA 2012 Chicago Meetings Paper.
  20. Thorsen, Ivar Sandvig. 2010. "Dry Bulk Shipping and Business Cycles." M. S. thesis., Norwegian School of Economics and Business Administration.
  21. Tsioumas, Vangelis, et al. 2017. "A Novel Approach to Forecasting the Bulk Freight Market." The Asian Journal of Shipping and Logistics 33(1):33-41. https://doi.org/10.1016/j.ajsl.2017.03.005
  22. Uyar, Kaan, and Ahmet Ilhan. 2016. "Long Term Dry Cargo Freight Rates Forecasting by using Recurrent Fuzzy Neural Networks." In: Aliev, R.A. et al., Procedia Computer Science, 12th International Conference on Application of Fuzzy Systems and Soft Computing (ICAFS 2016), Vienna, Austria, August 29-30, 2016, Elsevier: Oxford, United Kingdom, 102:642-647.
  23. Williams, Ronald J., and Jing Peng. 1990. "An Efficient Gradient-based Algorithm for On-line Training of Recurrent Network Trajectories." Neural Computation 2(4):490-501. https://doi.org/10.1162/neco.1990.2.4.490
  24. Zeng, Qingcheng, and Chenrui Qu. 2014. "An Approach for Baltic Dry Index Analysis Based on Empirical Mode Decomposition." Maritime Policy & Management 41(3):224-240. https://doi.org/10.1080/03088839.2013.839512
  25. Zeng, Qingcheng, et al. 2016. "A New Approach for Baltic Dry Index Forecasting Based on Empirical Mode Decomposition and Neural Networks." Maritime Economics & Logistics 18(2):192-210. https://doi.org/10.1057/mel.2015.2
  26. 2010. "Forecasting Freight Rates: Evidence from the Baltic Exchange Indices and the IMAREX Freight Futures." M.S. Thesis, University of Piraeus.