Search for Articles:
Journal:
Subject:
MOSP / Journal / Journal of International Economy and Global Governance

Journal Menu

Home
Aims & Scope
Editorial Board
For Authors
Ethics & Policies
APC & Subscription
Editorial Office

Journal Browser

Vol.2 (2025) Iss. 1 / 2
Vol.1 (2024) Iss. 1 / 2 / 3 / 4 / 5 / 6 / 7 / 8

Table of Contents

Abstract
Funding
Conflicts of Interest
References
License
Open Access
文章

Research on BDI Index Prediction Based on LSTM Neural Network

Wenjie Li1,*, HaiBo Bao2，Xinge Lei3

1 Department of Economy, Party School of Zhejiang Provincial Committee of C.P.C, Hangzhou, China
2 Department of Economy, Party School of Zhejiang Provincial Committee of C.P.C, Hangzhou, China
3 Department of Economy, Party School of Zhejiang Provincial Committee of C.P.C, Hangzhou, China
* Correspondence: Wenjie Li, E-mail: jerome17398267942@163.com
 
J. Int. Eco. Glo. Gov., 2025, 2(1), 67-88; https://doi.org/10.12414/jiegg.250438
Received : 17 Nov 2024 / Revised : 05 Dec 2024 / Accepted : 05 Dec 2024 / Published : 25 Feb 2025
© The Author(s). Published by MOSP. This is an open access article under the CC BY-NC license.
Download
Cite
Abstract
 
This study utilizes the Long Short-Term Memory (LSTM) neural network model to predict the Baltic Dry Index (BDI), a crucial indicator of the global economy and international trade. By analyzing historical data and related economic indicators of the BDI, a dataset incorporating multiple time series characteristics was constructed. The study finds that a univariate LSTM model demonstrates higher accuracy and stability in predicting the BDI index due to its ability to capture nonlinear dynamic features. This model can provide market trend forecasts for investors, assist in formulating investment strategies, and support economic policy decisions for government policymakers in adapting to changes in international trade and shipping markets. The results indicate that the LSTM model has practical value in financial market forecasting and offers a new direction for the application of deep learning technology in this field.
 
Keywords: Shipping Market, LSTM Model, BDI Index, Index Forecasting
 
Download the full text PDF for viewing and using it according to the license of this paper.

Funding

    None.

Conflicts of Interest:

    The authors declare that they have no conflicts of interest to report regarding the present study.

References

  1. Gao, Ruzhao, Yueqiang Zhao, and Bing Zhang. 'Baltic dry index and global economic policy uncertainty: evidence from the linear and nonlinear Granger causality tests', Applied Economics Letters, 2023. 30: 360-66.
  2. Zeng, Qingcheng, and Chenrui Qu. 'An approach for Baltic Dry Index analysis based on empirical mode decomposition', Maritime Policy & Management, 2014. 41: 224-40.
  3. Gu, YM., "Baltic Dry Index and iron ore spot market: dynamics and interactions." Applied Economics (2019). 51(35): 3855-3863.
  4. Chang, C.-W. "Exploring the Factors Influencing the Impact of the COVID-19 Pandemic on Global Shipping: A Case Study of the Baltic Dry Index." Sustainability (2023).15(14).
  5. Papailias, F. "The Baltic Dry Index: cyclicalities, forecasting and hedging strategies." Empirical Economics (2017). 52(1): 255-282.
  6. Bae, S.-H., G. Lee, and K.-S. Park, A Baltic Dry Index Prediction using Deep Learning Models. Journal of Korea Trade, 2021. 25(4): p. 17-36.
  7. Ma Shaohui, Sun Yanan. Cointegration Test and Causal Analysis between World Dry Bulk Ship Orders, Baltic Dry Index, and Second-hand Ship Transaction Volume [J]. China Shipbuilding,2017,58(04):203-213.
  8. Lan Xiangang. Research on the Prediction of Shipping Freight Index under the Influence of International Oil Prices — Analysis Based on the SVR-Adam-LSTM Model [J]. Price: Theory & Practice.2023(01):74-78+193.
  9. Liu Bin, Liu Chao, Wan Zhong, et al. The Correlation between BDI Index and Shanghai Composite Index [J]. Journal of Dalian Maritime University.2010,36(03):35-38.
  10. Meng Bin, Lin Xiaoqian, Kuang Haibo, et al. The Long Memory Linkage Effect of Economic Policy Uncertainty on Shipping Market and Financial Market [J]. Systems Engineering Theory & Practice. 2023, (7): 1927-1939
  11. Huang Jingxuan, Zhang Chenliang. Correlation Analysis of the Impact of BDI on the Prosperity of Chinese Shipping Enterprises [J]. China Logistics and Procurement.,2019, (24):122.
  12. Xiao Huiwen. A Study on the Correlation between International Dry Bulk Shipping Freight and China's Ore Import and Export Trade [D]. Chongqing Technology and Business University.,2023.
  13. Li Hongkang. A Study on the Dynamic Correlation between BDI Dry Bulk Index and Commodity Prices [D]. Harbin Engineering University.,2020.
  14. Ai Lin, Lv Jingye, Matalinah Mwamlima. A Study on the Correlation between Baltic Freight Index and Carbon Price [J]. Coal Economic Research, 2022, 42(02): 11-16.
  15. Zhang Yongfeng, Zhao Gang, Chen Jihong. An Exploration of the Correlation between Baltic Dry Index and Shanghai Composite Index [J]. Price Theory and Practice, 2016(09): 120-123.
  16. Wang Xian. Research on BDI Index Forecasting Based on EMD-XGBoost Model [D]. Dalian University of Maritime, 2023.
  17. Ning Jintao. A Study on the Spillover Effect between Shipping Forward Freight and Commodity Futures Market [D]. Dalian University of Maritime, 2022.
  18. Han Jian. A Study on the Cyclical Fluctuations of BDI Index and Its Influencing Factors [D]. East China Normal University, 2018.
  19. Wu Huahua, Kuang Haibo, Song Yang. BDI Index Forecasting Based on VMD-FFT-LSTM Model [J]. Journal of Dalian Maritime University, 2019, 45(03): 9-16.
  20. Yang Chen, Chen Guici. Forecasting International Gold Futures Prices Based on EMD-LSTM [J]. Journal of South-Central University for Nationalities (Natural Science Edition), 2023, 42(06): 857-864.
  21. Yang Qing, Wang Chenwei. A Study on Global Stock Index Forecasting Based on Deep Learning LSTM Neural Network [J]. Statistical Research, 2019, 36(03): 65-77.
  22. Peng Yan, Liu Yuhong, Zhang Rongfen. Modeling and Analysis of Stock Price Prediction Based on LSTM [J]. Computer Engineering and Applications, 2019, 55(11): 209-212.
  23. Ouyang Hongbing, Li Wen. A Study on the Application of Blockchain Technology in China's Inclusive Finance [J]. Wuhan Finance, 2018(04): 36-40.
  24. Li Jia, Huang Zhihao, Chen Donglan. A Study on Stock Index Forecasting Based on LSTM and Other Deep Learning Methods [J]. Software Guide, 2019, 18(09): 17-21.​​​​​​​
  25. Zhang Wei. Research on Shanghai Composite Index Forecasting Method Based on Stacking Ensemble Algorithm [D]. Dongbei University of Finance and Economics, 2022.
  26. Zhao Yang, Li Yan, Zhang Chaoyang, et al. An Interpretable Yield Prediction Model [J]. Systems Engineering, 2024, 42(01): 130-138.
  27. Yao Honggang, Mu Nianguo. Forecasting Financial Time Series with EMD-LSTM Model [J]. Computer Engineering and Applications, 2021, 57(05): 239-244
  28. Wang Jungang, Hu Baiqing, Gaodunyang, et al. A Method for Ship Trajectory Forecasting Based on LSTM-EMD Model [J]. Ship Electronic Engineering, 2023, 43(07): 29-35.
  29. Fan Yonghui, Xing Yuwei, Yang Hualong. Forecasting Baltic Dry Bulk Freight Index Based on GARCH Model [J]. Practice and Recognition of Mathematics, 2015, 45(07): 42-47.
  30. Wang Xuan, Cai Junling, Tang Ling, et al. A Study on VaR Risk Measurement of Stock Portfolio Based on BEMD-Copula-GARCH Model [J]. Systems Engineering Theory and Practice, 2017, 37(02): 303-310.
  31. Wang Dashan, Liu Wenbai. A Study on the Development Trend of International Dry Bulk Shipping Market — Analysis Based on Principal Variable-Autoregressive Model [J]. Research on Technological Economics and Management, 2021, (04): 83-88.
  32. Wang Dashan, Liu Wenbai. A Study on the Development and BDI Index Forecasting of International Dry Bulk Shipping Market — Analysis Based on Simultaneous Equation Model [J]. Price Theory and Practice, 2018, (06): 78-81.
  33. Dong Liangcai, Huang Youfang, Hu Hao. A Study on Shipping Freight Index Forecasting Based on Fuzzy Neural Network [J]. Journal of Dalian Maritime University, 2010, 36(04): 31-34. Katris, Christos, and Manolis G. Kavussanos. 'Time series forecasting methods for the Baltic dry index', Journal of Forecasting, 2021. 40: 1540-65.
  34. Lee, S.-W. and J.S. Kim, An Analysis on Relationship between BDI and Financial Markets of Korea. International Area Studies Review, 2014. 18(1): p. 181-200.
  35. Tiwari, A.K., Do shipping freight markets impact commodity markets? International Review of Economics & Finance, 2024. 91: p. 986-1014.
  36. Carriere-Swallow, Y., et al., Shipping costs and inflation. Journal of International Money and Finance, 2023. 130.
  37. Chen, Y., J. Xu, and J. Miao, Dynamic volatility contagion across the Baltic dry index, iron ore price and crude oil price under the COVID-19: A copula-VAR-BEKK-GARCH-X approach. Resources Policy, 2023. 81.
  38. Zhao, H.-M.Measuring the impact of an exogenous factor: An exponential smoothing model of the response of shipping to COVID-19. Transport Policy, 2022. 118: p. 91-100.
  39. Makridakis, S. A novel forecasting model for the Baltic dry index utilizing optimal squeezing. Journal of Forecasting, 2020. 39(1): p. 56-68.
  40. Han, L., L. Wan, and Y. Xu, Can the Baltic Dry Index predict foreign exchange rates? Finance Research Letters, 2020. 32.
© The Author(s). Published by MOSP. 
This is an open access article under the CC BY-NC license.

Li, W.; Bao, H.; Lei, X. Research on BDI Index Prediction Based on LSTM Neural Network. Journal of International Economy and Global Governance 2025, 2 (1), 67-88. https://doi.org/10.12414/jiegg.250438.

Subscribe Your Manuscript
Branches
HanLin Group
澳科中文官网
Book Center
Patent Center
Services
For Authors
Book Builder
Projects
Young Mind
Beyond Expo.
About us
MOSP Team
MOAJ Team
Blog & News
Partnership
Careers
Contact
© 2021-2023 Macao Scientific Publishers ( Macao, P.R. China )
www.mospbs.com