Research on Shipping Investor Sentiment Index Based on PCA+RBM

DOI

10.2991/978-94-6463-958-2_23How to use a DOI?

Keywords

Shipping investor sentiment; RBM; PCA; feature extraction

Abstract

Developing a shipping investor sentiment index is of great significance as it helps market participants better grasp market volatility, avoid potential risks. The research focuses on the shipping market, with particular emphasis on the Baltic Dry Index (BDI), which plays a central role in global trade and economic activities. We have taken into account a wide range of key factors that influence the shipping market, including market supply and demand, economic policy uncertainty, geopolitical risks, and investor attention. By leveraging data science tools such as Principal Component Analysis (PCA) and Restricted Boltzmann Machine (RBM), and combining them with regression analysis, we aim to extract and reduce the key features in shipping market data, thereby constructing a robust shipping investor sentiment index. The innovations of this paper are threefold. First, we have established a comprehensive shipping investor sentiment index system by integrating multiple factors such as market supply and demand, economic policy uncertainty, geopolitical risks, and investor attention. Second, we introduce a novel approach by incorporating regression analysis, PCA, and RBM to construct the shipping investor sentiment index based on data feature extraction and dimensionality reduction. Third, our empirical analysis reveals that the sentiment index constructed in this paper serves as a Granger cause of the Baltic Dry Index, indicating that the fluctuations of the sentiment index precede those of the freight index. These findings not only enrich the existing literature on shipping investor sentiment but also provide valuable insights for market participants to better understand and navigate the complexities of the shipping market.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Yuhang Che
AU  - Xiaoxing Gong
AU  - Liang Dong
PY  - 2025
DA  - 2025/12/26
TI  - Research on Shipping Investor Sentiment Index Based on PCA+RBM
BT  - Proceedings of the 5th International Conference on Management Science and Software Engineering (ICMSSE 2025)
PB  - Atlantis Press
SP  - 195
EP  - 207
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-958-2_23
DO  - 10.2991/978-94-6463-958-2_23
ID  - Che2025
ER  -