Long Short-Term Memory를 활용한 건화물운임지수 예측
Prediction of Baltic Dry Index by Applications of Long Short-Term Memory
0
조회
0
다운로드
9
인용
0
참고문헌
키워드
초록
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 (BDI time series) at point of time by 8 variables (related to the dry bulk market) of at point of time . 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.
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 (BDI time series) at point of time by 8 variables (related to the dry bulk market) of at point of time . 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.
참고문헌 (27)
- Scarsi, Roberta, "The Bulk Shipping Business : Market Cycles and Shipowners’ Biases", Maritime Policy & Management, 34(6), pp.577~590 (2007)
- Chistè, Claudio, "Investigating the Cyclical Behavior of the Dry Bulk Shipping Market", Maritime Policy & Management, 41(1), pp.1~19 (2014)
- Courbariaux, Matthieu, "Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or –1", arXiv, preprint arXiv:1602.02830:1-11, ~ (2016)
- Cullinane, K. P. B., "A Comparison of Models for Forecasting the Baltic Freight Index: Box-Jenkins Revisited", International Journal of Maritime Economics, 1(2), pp.15~39 (1999)
- Elman, Jeffrey L, "Finding Structure in Time", Cognitive Science, 14(2), pp.179~211 (1990)
- Fan, Yong Hui, "Prediction of Baltic Capesize Freight Index Based on GARCH Model", Applied Mechanics and Materials, 488, pp.1494~1497 (2014)
- Geman, Hélyette, "Shipping Markets and Freight Rates: An Analysis of the Baltic Dry Index", Journal of Alternative Investments, 15(1), pp.98~109 (2012)
- HAN, Minsoo, "Prediction of Baltic Dry Index by Applications of Long Short-Term Memory Recurrent Neural Network Architectures", M.S., pp.2019
- Hochreiter, Sepp, "Long short-term memory", Neural Computation, 9(8), pp.1735~1780 (1997)
- Hochreiter, Sepp, "Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-term Dependencies", pp.1~15 (2001)
- Jordan, Michael I, "Serial Order: A Parallel Distributed Processing Approach", Advances in Psychology, 121, pp.471~495 (1997)
- Kavussanos, Manolis G., "Seasonality Patterns in Dry Bulk Shipping Spot and Time Charter Freight Rates", Transportation Research Part E: Logistics and Transportation Review, 37(6), pp.443~467 (2001)
- Kavussanos, Manolis G., "Seasonality Patterns in Tanker Spot Freight Rate Markets", Economic Modelling, 19(5), pp.747~782 (2002)
- Leonov, Yordan, "A Wavelet and Neural Network Model for the Prediction of Dry Bulk Shipping Indices", Maritime Economics & Logistics, 14(3), pp.319~333 (2012)
- Li, Jun, "Forecasting Tanker Freight Rate using Neural Networks", Maritime Policy & Management, 24(1), pp.9~30 (1997)
- Lin, Faqin, "Trade, Income and the Baltic Dry Index", European Economic Review, 59, pp.1~18 (2013)
- Lyridis, D. V., "Forecasting Tanker Market using Artificial Neural Networks", Maritime Economics & Logistics, 6(2), pp.93~108 (2004)
- Papailias, Fotis, "The Baltic Dry Index: cyclicalities, forecasting and hedging strategies", Empirical Economics, 52(1), pp.255~282 (2017)
- Bakshi, Gurdip S., "The Baltic Dry Index as a Predictor of Global Stock Returns, Commodity Returns, and Global Economic Activity", AFA 2012 Chicago Meetings Paper (2011)
- Thorsen, Ivar Sandvig, "Dry Bulk Shipping and Business Cycles", M. S., pp.2010
- Vangelis TSIOUMAS, "A Novel Approach to Forecasting the Bulk Freight Market", The Asian Journal of Shipping and Logistics, 33(1), pp.33~41 (2017), 한국해운물류학회
- Uyar, Kaan, "Long Term Dry Cargo Freight Rates Forecasting by using Recurrent Fuzzy Neural Networks", Procedia Computer Science, 12th International Conference on Application of Fuzzy Systems and Soft Computing (ICAFS 2016), 102, pp.642~647 (2016)
- Williams, Ronald J., "An Efficient Gradient-based Algorithm for On-line Training of Recurrent Network Trajectories", Neural Computation, 2(4), pp.490~501 (1990)
- Zeng, Qingcheng, "An Approach for Baltic Dry Index Analysis Based on Empirical Mode Decomposition", Maritime Policy & Management, 41(3), pp.224~240 (2014)
- Zeng, Qingcheng, "A New Approach for Baltic Dry Index Forecasting Based on Empirical Mode Decomposition and Neural Networks", Maritime Economics & Logistics, 18(2), pp.192~210 (2016)
- Γούλας, Λάμπρος, "Forecasting Freight Rates: Evidence from the Baltic Exchange Indices and the IMAREX Freight Futures", M.S., pp.2010