Understanding the Baltic Dry Index (BDI): an explainable decomposition approach

被引:0
|
作者
Guan, Linfei [1 ]
Zhao, Ziao [2 ]
Sun, Qinghe [2 ]
机构
[1] Northwestern Polytech Univ, Sch Management, Xian, Peoples R China
[2] Hong Kong Polytech Univ, Fac Business, Dept Logist & Maritime Studies, Kowloon, Hong Kong, Peoples R China
关键词
Shipping finance; maritime freight; seasonality; Prophet forecasting; explainable AI; VOLATILITY; MARKETS; TRENDS; MODEL;
D O I
10.1080/03088839.2024.2448446
中图分类号
U [交通运输];
学科分类号
08 ; 0823 ;
摘要
The Baltic Dry Index (BDI) is a crucial indicator of the dry bulk freight market, offering insights into the shipping industry's health and activity levels. In this study, we introduce an explainable decomposition framework to unveil the underlying mechanisms of BDI dynamics. Utilizing historical data from 1 November 1999, to 5 March 2024, we decompose BDI into trends, seasonal fluctuations, and externally derived influences. Our experiments have identified the magnitude of trend changes from major global events over the past two decades. Intriguingly, we find that advancements in industry and technology contribute significantly to upward trends in BDI. We also explore BDI's seasonality, identifying distinct cyclical patterns within a year, including the Christmas and Chinese New Year effects, and more interestingly, a trough in late June due to the receding in shipping demand for the three major bulk. Our findings further offer valuable insights into understanding BDI fluctuations, aiding decision-making processes in the maritime freight market. We find that Natural Gas and the Dollar Index are potent signals for BDI one week to one month ahead, while the NASDAQ 100 Index emerges as a leading indicator for longer forecasting horizons.
引用
收藏
页数:25
相关论文
共 50 条
  • [41] Understanding determinants of socioeconomic inequality in mental health in Iran's capital, Tehran: a concentration index decomposition approach
    Esmaeil Khedmati Morasae
    Ameneh Setareh Forouzan
    Reza Majdzadeh
    Mohsen Asadi-Lari
    Ahmad Ali Noorbala
    Ahmad Reza Hosseinpoor
    International Journal for Equity in Health, 11
  • [42] An explainable artificial intelligence approach to understanding drivers of economic energy consumption and sustainability
    Srivastava, Praveen Ranjan
    Mangla, Sachin Kumar
    Eachempati, Prajwal
    Tiwari, Aviral Kumar
    ENERGY ECONOMICS, 2023, 125
  • [43] Conceptualizing understanding in explainable artificial intelligence (XAI): an abilities-based approach
    Speith, Timo
    Crook, Barnaby
    Mann, Sara
    Schomaecker, Astrid
    Langer, Markus
    ETHICS AND INFORMATION TECHNOLOGY, 2024, 26 (02)
  • [44] A fuzzy neural network combined with technical indicators and its application to Baltic Dry Index forecasting
    Chou, Chien-Chang
    Lin, Keng-Shou
    JOURNAL OF MARINE ENGINEERING AND TECHNOLOGY, 2019, 18 (02): : 82 - 91
  • [45] DYNAMICS OF ECONOMIC ADJUSTMENT UNDER UNCERTAINTY: MS-VAR MODEL FOR BALTIC DRY INDEX
    Kornilov, Sergei
    Ridala, Svetlana
    Aasma, Ants
    SGEM 2016, BK 2: POLITICAL SCIENCES, LAW, FINANCE, ECONOMICS AND TOURISM CONFERENCE PROCEEDINGS, VOL V, 2016, : 189 - 196
  • [46] Development of Decomposition Approach for Comprehensive Understanding of Drug Effects
    Mizuno, Tadahaya
    YAKUGAKU ZASSHI-JOURNAL OF THE PHARMACEUTICAL SOCIETY OF JAPAN, 2022, 142 (10): : 1077 - 1082
  • [47] Understanding inequalities in child immunization in India: a decomposition approach
    Joseph, Vinod Joseph Kannankeril
    JOURNAL OF BIOSOCIAL SCIENCE, 2022, 54 (03) : 371 - 383
  • [48] A Decomposition Approach for Risk-Averse Index Selection
    Schlosser, Rainer
    Halfpap, Stefan
    PROCEEDINGS OF THE 32TH INTERNATIONAL CONFERENCE ON SCIENTIFIC AND STATISTICAL DATABASE MANAGEMENT, SSDBM 2020, 2020,
  • [49] A generalized Fisher index approach to energy decomposition analysis
    Ang, BW
    Liu, FL
    Chung, HS
    ENERGY ECONOMICS, 2004, 26 (05) : 757 - 763
  • [50] The Concordance Index decomposition: A measure for a deeper understanding of survival prediction models
    Alabdallah, Abdallah
    Ohlsson, Mattias
    Pashami, Sepideh
    Roegnvaldsson, Thorsteinn
    ARTIFICIAL INTELLIGENCE IN MEDICINE, 2024, 148