순환신경망을 활용한 벙커유가 예측에 관한 연구
A Study on the Forecasting of Bunker Price Using Recurrent Neural Network
0
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
본 논문에서는 딥러닝 기반의 순환신경망을 이용하여 선박 연료유 예측을 시도하였다. 해운업에서는 선박 운항비에서 연료유가 차지하는 비중이 가장 크고 가격 변동성도 크기 때문에, 해운기업은 합리적이고 과학저인 방법으로 연료유를 예측하여 시장경쟁력을 확보할 수 있다. 본 논문에서는 순환신경망 모델 3가지(RNN, LSTM, GRU)를 이용하여 싱가폴의 HSFO 380CST 벙커유 가격을 단기 예측하였다. 예측결과, 첫째, 선박 연료유 단기적 예측을 위해서는 장기 메모리를 사용하는 LSTM, GRU보다는 일반적인 RNN 모델의 성능이 우수한 것으로 분석되어, 장기적 정보의예측 기여가 낮은 것으로 분석되었다. 둘째, 계량경제학 모델을 사용한 선행연구와 비교하여 순환신경망 모델의 예측성능이 우수한 것으로 분석되어 연료유가의 비선형적 특성을 고려한 순환신경망 모델을 통한 예측 연구의 필요성을 확인하였다. 연구의 결과는 선박 연료유의 단기 예측을 통하여 해운기업의 선박 연료유 수급 결정과 같은 의사결정에 도움이 될 수 있을 것으로 기대된다.
Abstract
In this paper, we propose the deep learning-based neural network model to predict bunker price. In the shipping industry, since fuel oil accounts for the largest portion of ship operation costs and its price is highly volatile, so companies can secure market competitiveness by making fuel oil purchasing decisions based on rational and scientific method. In this paper, short-term predictive analysis of HSFO 380CST in Singapore is conducted by using three recurrent neural network models like RNN, LSTM, and GRU. As a result, first, the forecasting performance of RNN models is better than LSTM and GRUs using long-term memory, and thus the predictive contribution of long-term information is low. Second, since the predictive performance of recurrent neural network models is superior to the previous studies using econometric models, it is confirmed that the recurrent neural network models should consider nonlinear properties of bunker price. The result of this paper will be helpful to improve the decision quality of bunker purchasing.
참고문헌 (21)
- M. Stopford, "Maritime Economics", pp.233~ (2009), Taylor & Francis
- Theo E. Notteboom, "The effect of high fuel costs on liner service configuration in container shipping", Journal of Transport Geography, 17(5), pp.325~337 (2009), Elsevier BV[DOI]
- A. H. Alizadeh, "Shipping Derivatives and Risk Management", pp.338~362 (2021), Palgrave MacMillan
- D Ronen, "The effect of oil price on containership speed and fleet size", Journal of the Operational Research Society, 62(1), pp.211~216 (2017), Informa UK Limited[DOI]
- Amir H. Alizadeh, "Hedging against bunker price fluctuations using petroleum futures contracts: constant versus time-varying hedge ratios", Applied Economics, 36(12), pp.1337~1353 (2006), Informa UK Limited[DOI]
- Ch.N. Stefanakos, "Forecasting bunker prices; A nonstationary, multivariate methodology", Transportation Research Part C: Emerging Technologies, 38, pp.177~194 (2014), Elsevier BV[DOI]
- Christos Stefanakos, "Fuzzy time series forecasting of bunker prices", WMU Journal of Maritime Affairs, 14(1), pp.177~199 (2015), Springer Science and Business Media LLC[DOI]
- 최정석, "시스템 다이내믹스를 활용한 선박 연료유 가격 예측", 한국항만경제학회지, 33(1), pp.75~87 (2017), 한국항만경제학회[DOI]
- D. E. Rumelhart, "Learning representations by back-propagating errors", Nature, 323, pp.533~536 (1986)
- S. Hochreiter, "Long short-term memory", Neural Computation, 9(8), pp.1735~1780 (1997)[DOI]
- K. Cho, "Learning phrase representations using RNN Encoder-Decoder for statistical machine translation", arXiv:1406.1078, 1724~1734 (2014)
- 김도희, "딥러닝을 활용한 건화물선 운임 지수 예측", 대한산업공학회지, 45(2), pp.111~116 (2019), 대한산업공학회[DOI]
- 한민수, "Long Short-Term Memory를 활용한 건화물운임지수 예측", 품질경영학회지, 47(3), pp.497~508 (2019), 한국품질경영학회[DOI]
- 임상섭, "순환신경망 모델을 활용한 벌크 운임지수 예측", 해양비즈니스, (40), pp.159~180 (2018), 한국해양비즈니스학회
- G. Cybenko, "Approximation by superpositions of a sigmoidal function", Mathematics of Control, Signals, and Systems, 2(4), pp.303~314 (1989), Springer Science and Business Media LLC[DOI]
- Guoqiang Zhang, "Forecasting with artificial neural networks:", International Journal of Forecasting, 14(1), pp.35~62 (1998), Elsevier BV[DOI]
- L. Yu, "Assessing Potentiality of Support Vector Machine Method in Crude Oil Price Forecasting", Eurasia Journal of Mathematics, Science and Technology Education, 13(12), pp.7893~7904 (2017)[DOI]
- Güleryüz, D., "The prediction of Brent crude oil trend using LSTM and Facebook prophet", European Journal of science and Technology, 20, pp.303~314 (2020)
- Yu-Xi Wu, "Improved EEMD-based crude oil price forecasting using LSTM networks", Physica A: Statistical Mechanics and its Applications, 516, pp.114~124 (2019), Elsevier BV[DOI]
- Hualing Lin, "Crude Oil Prices Forecasting: An Approach of Using CEEMDAN-Based Multi-Layer Gated Recurrent Unit Networks", Energies, 13(7), pp.1543~ (2020), MDPI AG[DOI]
- Lean Yu, "Forecasting crude oil price with an EMD-based neural network ensemble learning paradigm", Energy Economics, 30(5), pp.2623~2635 (2008), Elsevier BV[DOI]