DOI QR코드

DOI QR Code

Estimation Model for Freight of Container Ships using Deep Learning Method

딥러닝 기법을 활용한 컨테이너선 운임 예측 모델

  • Kim, Donggyun (Division of Navigation Science, Mokpo National Maritime University) ;
  • Choi, Jung-Suk (Division of Maritime Transportation, Mokpo National Maritime University)
  • 김동균 (목포해양대학교 항해학부) ;
  • 최정석 (목포해양대학교 해상운송학부)
  • Received : 2021.07.19
  • Accepted : 2021.08.27
  • Published : 2021.08.31

Abstract

Predicting shipping markets is an important issue. Such predictions form the basis for decisions on investment methods, fleet formation methods, freight rates, etc., which greatly affect the profits and survival of a company. To this end, in this study, we propose a shipping freight rate prediction model for container ships using gated recurrent units (GRUs) and long short-term memory structure. The target of our freight rate prediction is the China Container Freight Index (CCFI), and CCFI data from March 2003 to May 2020 were used for training. The CCFI after June 2020 was first predicted according to each model and then compared and analyzed with the actual CCFI. For the experimental model, a total of six models were designed according to the hyperparameter settings. Additionally, the ARIMA model was included in the experiment for performance comparison with the traditional analysis method. The optimal model was selected based on two evaluation methods. The first evaluation method selects the model with the smallest average value of the root mean square error (RMSE) obtained by repeating each model 10 times. The second method selects the model with the lowest RMSE in all experiments. The experimental results revealed not only the improved accuracy of the deep learning model compared to the traditional time series prediction model, ARIMA, but also the contribution in enhancing the risk management ability of freight fluctuations through deep learning models. On the contrary, in the event of sudden changes in freight owing to the effects of external factors such as the Covid-19 pandemic, the accuracy of the forecasting model reduced. The GRU1 model recorded the lowest RMSE (69.55, 49.35) in both evaluation methods, and it was selected as the optimal model.

해운 시황을 예측하는 것은 중요한 문제이다. 투자 방식의 결정, 선대 편성 방법, 운임 등을 결정하기 위한 판단 근거가 되며 이는 기업의 이익과 생존에 큰 영향을 미치기 때문이다. 이를 위해 본 연구에서는 기계학습 모델인 장단기 메모리 및 간소화된 장단기 메모리 구조의 Gated Recurrent Units를 활용하여 컨테이너선의 해상운임 예측 모델을 제안한다. 운임 예측 대상은 중국 컨테이너 운임지수(CCFI)이며, 2003년 3월부터 2020년 5월까지의 CCFI 데이터를 학습에 사용하였다. 각 모델에 따라 2020년 6월 이후의 CCFI를 예측한 후 실제 CCFI와 비교, 분석하였다. 실험 모델은 하이퍼 파라메터의 설정에 따라 총 6개의 모델을 설계하였다. 또한 전통적인 분석 방법과의 성능을 비교하기 위해 ARIMA 모델도 실험에 추가하였다. 최적 모델은 두 가지 방법에 따라 선정하였다. 첫 번째 방법으로 각 모델을 10회 반복 실험하여 얻은 RMSE의 평균값이 가장 작은 모델을 선정하는 것이다. 두 번째 방법으로는 모든 실험에서 가장 낮은 RMSE를 기록한 모델을 선정하는 것이다. 실험 결과 전통적 시계열 예측모델인 ARIMA 모델과 비교하여 딥러닝 모델의 정확도를 입증하였으며, 정확한 예측모델을 통해 운임 변동의 위험관리 능력을 제고시키는데 기여했다. 반면 코로나19와 같은 외부 효과에 따른 운임의 급격한 변화상황이 발생한 경우, 예측모델의 정확도가 감소하는 한계점을 나타냈다. 제안된 모델 중 GRU1 모델이 두 가지 평가 방법 모두에서 가장 낮은 RMSE(69.55, 49.35)를 기록하며 최적 모델로 선정되었다.

Keywords

Acknowledgement

This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. NRF-2020R1G1A1004161).

References

  1. Ahn, Y. and B. Ko(2018), Analysis of Factors Affecting on the Freight Rate of Container Carriers, Korea Trade Research Association, Vol. 43, No. 5, pp. 159-177.
  2. Alsharif, M. H., M. K. Younes, and J. Kim(2019), Time Series ARIMA Model for Prediction of Daily and Monthly Average Global Solar Radiation: The Case Study of Seoul, South Korea, Symmetry, Vol. 11, No. 2, https://doi.org/10.3390/sym11020240.
  3. Apaydin, H., H. Feizi, M. T. Sattari, M. S. Colak, S. Shamshirband, and K. Chau(2020), Comparative Analysis of Recurrent Neural Network Architectures for Reservoir Inflow Forecasting, Journal of Water, Vol. 12, No. 5, https://doi.org/10.3390/w12051500.
  4. Beenstock, M. and A. Vergottis(1989), An Econometric Model of the World Tanker Market, Journal of Transport Economics and Policy, Vol. 23, No. 3, pp 263-280.
  5. Britz, D., A. Goldie, M. Luong, and Q. Le(2017), Massive Exploration of Neural Machine Translation Architectures, Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 1442-1451.
  6. Choe, Y. and I. S. Kim(2016), Derivation of Selection Factors of Cruise Home port in Asia Using Delphi Technique, Korea academic society of tourism management, Vol. 31, No. 8, pp. 199-218.
  7. Choi, J. S. and D. G. Hwang(2017), Development of Korean Container Freight Index Based on Trade Volume, Journal of Korea Port Economic Association, Vol. 33, No. 3, pp.53-66. https://doi.org/10.38121/kpea.2017.09.33.3.53
  8. Chung, J., C. Gulcehre, K. H. Cho, and Y. Bengio(2014), Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling, Cornell University, Neural and Evolutionary Computing, arXiv:1412,3555.
  9. Cochrane, J. H.(1997), Time Series for Macroeconomics and Finance, Graduate School of Business, University of Chicago.
  10. David, M., F. Ramahatana, P. J. Trombe, and P. Lauret(2016), Probabilistic forecasting of the solar irradiance with recursive ARMA and GARCH models, Solar Energy, Vol. 133, pp. 55-72. https://doi.org/10.1016/j.solener.2016.03.064
  11. Duru, O. and S. Yoshida(2011), Centennial Decline of Shipping Freight Rates and Life Cycle Effect: Theory of Long Term Cycles, Vol. 3, No. 2, pp. 59-77.
  12. Duru, O., E. Bulut, and S. Yoshid(2010), Bivariate long term fuzzy time series forecasting of dry cargo freight rates, The Asian Journal of Shipping and Logistics, Vol. 26, No. 2, pp. 205-223. https://doi.org/10.1016/S2092-5212(10)80002-1
  13. Eslami, P., K. Jung, D. Lee, and A. Tjolleng(2017), Predicting tanker freight rates using parsimonious variables and a hybrid artificial neural network with an adaptive genetic algorithm, Maritime Economics & Logistics, Vol. 19, No. 3, pp. 538-550. https://doi.org/10.1057/mel.2016.1
  14. Fan, S., T. Ji, W. Gordon, and B. Rickard(2013), Forecasting Baltic Dirty Tanker Index by Applying Wavelet Neural Networks, Journal of Transportation Technologies, Vol. 3, No. 1, pp. 68-87. https://doi.org/10.4236/jtts.2013.31008
  15. Fayle, E. C.(1933), A short history of the world's shipping industry, London: George Allen & Unwin.
  16. Fu, R., Z. Zhang, and L. Li(2018), Using LSTM and GRU Neural Network Methods for Traffic Flow Prediction, 31st Youth Academic Annual Conference of Chinese Association of Automation (YAC).
  17. George, M.(2021), Forecasting oil tanker shipping market in crisis periods: Exponential smoothing model application, The Asian Journal of Shipping and Logistics, Available online 30 June 2021.
  18. Hayashi, K.(2020), Stationarity of spot freight rates considering supply/demand effect, Journal of Shipping and Trade, Vol. 5, No. 24, https://doi.org/10.1186/s41072-020-00078-8.
  19. Hochreiter, S. and J. Schmidhuber(1997), LONG SHORT-TERM MEMORY, Neural Computation, Vol. 9, No. 8, pp. 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  20. Kavussanos, M. G. and D. A. Tsouknidis(2014), The determinants of credit spreads changes in global shipping bonds, Transportation Research Part E: Logistics and Transportation Review, Vol. 70, pp. 55-75. https://doi.org/10.1016/j.tre.2014.06.001
  21. Kim, D., H. Kim, S. Sim, Y. Choi, H. Bae, and H. Yun(2019), Prediction of Dry Bulk Freight Index Using Deep Learning, Journal of the Korean Institute of Industrial Engineers, Vol. 45, No. 2, pp. 111-116. https://doi.org/10.7232/JKIIE.2019.45.2.111
  22. Ko, B. and D. Kim(2019), Analysis of Container Shipping Market Using Multivariate Time Series Models, The Korea Port Economic Association, Vol. 35, No. 3, pp. 61-72.
  23. Li, K. X., Y. Xiao, S. L. Chen, W. Zhang, Y. Du, and W. Shi(2018), Dynamics and interdependencies among different shipping freight markets, Maritime Policy & Management, Vol. 45, No. 7, pp. 837-849. https://doi.org/10.1080/03088839.2018.1488187
  24. Lim, S. and H. Yun(2019), Forecasting Tanker Indices with ARIMA-SVM Hybrid Models, Journal of Korean Association of Financial Engineering, Vol. 17, No. 4, pp. 79-98.
  25. Mo, S. W.(2013), A Forecast of Shipping Business during the Year of 2013, Journal of Korea Port Economic Association, Vol. 29, No. 1, pp. 67-76.
  26. Rumelhart, D. E., P. Smolensky, J. L. Mcclelland, and G. E. Hinton(1986), Sequential thought processes in PDP models, pp. 3-57.
  27. Samjung KPMG Report(2020), COVID-19 Bussiness Report, Samsung KPMG.
  28. Stopford, M.(2009), Maritime Economics. 3rd Edition, Routledge, London.
  29. Yang, S., X. Yu, and Y. Zhou(2020), LSTM and GRU neural network performance comparison study, 2020 International Workshop on Electronic Communication and Artificial Intelligence (IWECAI).