Futures markets and the baltic dry index: A prediction study based on deep learning

被引:1
|
作者
Su, Miao [1 ]
Nie, Yufei [2 ]
Li, Jiankun [3 ]
Yang, Lin [4 ]
Kim, Woohyoung [5 ]
机构
[1] Kyung Hee Univ, Grad Sch Technol Management, Yongin 17104, South Korea
[2] Kyung Hee Univ, Grad Sch Biotechnol, Yongin 17104, South Korea
[3] Chung Ang Univ, Grad Sch Int Trade & Logist, Seoul 06974, South Korea
[4] Shandong Univ, Business Sch, Weihai, Peoples R China
[5] Hanyang Univ, Grad Sch Technol & Innovat Management, Seoul 04763, South Korea
关键词
Shipping market; China commodity futures market; Forecasting; Baltic dry index; Deep learning; CNN-BiLSTM-AM; COMMODITY FUTURES; ECONOMETRIC-MODEL; CARGO FREIGHT; VOLATILITY; CHINESE; NETWORK; PRICES; IMPACT; RISK;
D O I
10.1016/j.ribaf.2024.102447
中图分类号
F8 [财政、金融];
学科分类号
0202 ;
摘要
The Baltic Dry Index (BDI), representing the shipping sector, displays a notable sensitivity to Chinese commodity futures markets. Stakeholders must grasp the relationship between BDI and China's commodity futures markets. However, there is currently a lack of comprehensive evaluation of Chinese futures' forecasting performance. Therefore, we collected data on 17 major Chinese commodity futures from April 16, 2015, to December 27, 2022, and used CNN, BiLSTM, and AM to assess China's futures market's BDI prediction power. The CNN-BiLSTM-AM ensemble model emerged as the most accurate, R2 value of 95.3 %. This study highlights the Chinese futures market's ability to predict the global shipping index BDI and broadens our understanding of the financial market-maritime industry interplay. By monitoring fluctuations in China's futures market, shipping companies and regulators can make precise BDI predictions, offering a scientific foundation for policy adjustments and decision-making amidst future BDI shifts.
引用
收藏
页数:20
相关论文
共 50 条
  • [21] Comparison of Econometric Models and Artificial Neural Networks Algorithms for the Prediction of Baltic Dry Index
    Zhang, Xin
    Xue, Tianyuan
    Stanley, H. Eugene
    IEEE ACCESS, 2019, 7 : 1647 - 1657
  • [22] Study on the prediction and inverse prediction of detonation properties based on deep learning
    Yang, Zi-hang
    Rong, Ji-li
    Zhao, Zi-tong
    DEFENCE TECHNOLOGY, 2023, 24 : 18 - 30
  • [23] Study on the prediction and inverse prediction of detonation properties based on deep learning
    Zi-hang Yang
    Ji-li Rong
    Zi-tong Zhao
    Defence Technology, 2023, 24 (06) : 18 - 30
  • [24] An approach for Baltic Dry Index analysis based on empirical mode decomposition
    Zeng, Qingcheng
    Qu, Chenrui
    MARITIME POLICY & MANAGEMENT, 2014, 41 (03) : 224 - 240
  • [25] Leverage effect analysis of Baltic dry index based on EGARCH model
    Dalian Maritime University, China
    Yuwei, Xing, 1600, Journal of Chemical and Pharmaceutical Research, 3/668 Malviya Nagar, Jaipur, Rajasthan, India (06):
  • [26] Interpretable image-based deep learning for price trend prediction in ETF markets
    Zhang, Ruixun
    Zhao, Chaoyi
    Lin, Guanglian
    EUROPEAN JOURNAL OF FINANCE, 2023,
  • [27] Prediction of corn futures prices with decomposition and hybrid deep learning models
    Li, Feng
    Tang, Menghe
    KNOWLEDGE AND INFORMATION SYSTEMS, 2025, 67 (03) : 2427 - 2452
  • [28] Multi-decomposition in deep learning models for futures price prediction
    Song, Yuping
    Huang, Jiefei
    Xu, Yang
    Ruan, Jinrui
    Zhu, Min
    EXPERT SYSTEMS WITH APPLICATIONS, 2024, 246
  • [29] Asymmetric dynamics between the Baltic Dry Index and financial markets during major global economic events
    Abakah, Emmanuel Joel Aikins
    Abdullah, Mohammad
    Dankwah, Boakye
    Lee, Chi- Chuan
    NORTH AMERICAN JOURNAL OF ECONOMICS AND FINANCE, 2024, 72
  • [30] Prediction of Atmospheric Turbulence Refractive Index Structure Constant Based on Deep Learning
    Ma Shengjie
    Hao Shiqi
    Zhao Qingsong
    Xu Chenlu
    Xiao Junling
    24TH NATIONAL LASER CONFERENCE & FIFTEENTH NATIONAL CONFERENCE ON LASER TECHNOLOGY AND OPTOELECTRONICS, 2020, 11717