China futures market and world container shipping economy: An exploratory analysis based on deep learning

Zhenqing Su, Jiankun Li, Qiwei Pang and Miao Su

Research in International Business and Finance, 2025, vol. 76, issue C

Abstract: As globalization increases, the volatility of China's financial market is gradually affecting world trade and economic development. However, few studies have quantified the impact of China's commodity futures market on the global container shipping market outlook. Therefore, this study collects 45,966 points of daily data from January 4, 2016, to January 1, 2023, and mines the price prediction function of Chinese commodity futures market indicators on the Shanghai Container Freight Index (SCFI). Specifically, a deep learning integrated model is constructed by combining a convolutional neural network (CNN), a bi-directional long and short-term memory network (BILSTM), and an attentional mechanism (AM). The results show that the CNN-BILSTM-AM model can accurately identify nonlinear features in SCFI data using Chinese commodity futures market indicators. In addition, the model effectively captures the long-term dependence of SCFI changes with Chinese commodity futures. Finally, this study concludes that the integrated model outperforms the single CNN, LSTM, and BILSTM machine learning models and the combined CNN-LSTM and CNN-BILSTM models (R²= 94.8 %). We also observe that when using Shapley's additive interpretation (SHAP) framework to predict SCFI, Power Coal Futures (ZCF) and CSI 300 Index Futures (IFI) significantly influence the CNN-BILSTM-AM model. In summary, this study enriches the understanding of the interaction between the Chinese commodity futures market and the global container shipping industry. This study also highlights the price mining potential of Chinese futures market indicators in forecasting world shipping economic indices, thus opening new paths in the field of forecasting and management of world shipping economic indicators. The results provide a powerful decisional support and risk management tool for financial institutions, shipping companies, individual investors, and government policymakers.

Keywords: Forecast of economic indicators; SCFI; China futures market; Machine learning; Convolution Neural Network; Bi-directional Long and Short Time Memory; Attention Mechanism (search for similar items in EconPapers)
Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0275531925001266
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:riibaf:v:76:y:2025:i:c:s0275531925001266

DOI: 10.1016/j.ribaf.2025.102870

Access Statistics for this article

Research in International Business and Finance is currently edited by T. Lagoarde Segot

More articles in Research in International Business and Finance from Elsevier
Bibliographic data for series maintained by Catherine Liu ().