The Detection of BDI Index Hidden Periodicities: A VMD-GRGC-FFT Ensemble Methods

Abstract

Abstract:

It is significant to find out the periodic characteristics of BDI index, the benchmark index of global shipping market, in order to further understand the law of marine freight rate, forecast the trend of global shipping market and so on. In this study, the BDI index hidden periodicities are discussed in depth, and the main innovation points are: Firstly, the theoretical analysis framework of BDI index periodicities division and formation mechanism is proposed, and the BDI index periodicities fluctuation influence factors of three dimensions: demand side, supply side and non-economy factors, are analyzed. Secondly, the framework of BDI index long period, middle period and short period calculation based on VMD-GRGC-FFT is constructed. BDI index modal components are decomposed by means of Variational Mode Decomposition (VMD), the three synthesis components of low, medium and high frequency are reconstructed using Grey Relational Grades Cluster analysis (GRGC), and hidden average periodicities corresponding to the BDI index are detected through the Fast Fourier transform (FFT) model. Thirdly, we collect BDI index day/week/month data in 1985-2015 for empirical analysis. Results show that: the BDI index's long period is about 16 years, middle period is about 2-4 years and short period is about 0.4-0.6 years. At the same time, we predict that in the next few years after 2016, the BDI index will still be in the long period of the depression stage and the middle period of the recovery stage.

Key words: BDI index, periodicity, Variational Mode Decomposition (VMD), Grey Relational Grades Cluster (GRGC), Fast Fourier Transformation (FFT)

Yu Fangping, Kuang Haibo. The Detection of BDI Index Hidden Periodicities: A VMD-GRGC-FFT Ensemble Methods[J]. , 2017, 29(4): 213-225.

References

[1] Theodoulidis B., Diaz D. Analysis of The Baltic Exchange Dry Index Using Data Mining Techniques[DB/OL]. http://ssrn.com/abstract=2419097 or http://dx.doi.org/10.2139/ssrn.2419097, 2009
[2] Lin F., Sim N. C. S. Trade, Income and the Baltic Dry Index[J]. European Economic Review, 2013,59:1-18
[3] Denning K. C., Riley W. B., DeLooze J. P. Baltic Freight Futures: Random Walk or Seasonally Predictable?[J]. International Review of Economics & Finance, 1994,3(4):399-428
[4] Kavussanos M. G., Amir H., Alizadeh M. Seasonality Patterns in Dry Bulk Shipping Spot and Time Charter Freight Rates[J]. Transportation Research Part E, 2001,37(6):443-467
[5] Randers J., Göluke U. Forecasting Turning Points in Shipping Freight Rates: Lessons from 30 Years of Practical Effort[J]. System Dynamics Review, 2007,23(2/3):253-284
[6] Roberta S. The Bulk Shipping Business: Market Cycles and Shipowners' Biases[J]. Maritime Policy & Manage, 2007,34(6):577-590
[7] Stopford M. Maritime Economics[M]. London: Taylor & Francis, 2008
[8] 马硕(瑞典). 航运市场周期理论与当今干散货航运市场变化[J]. 水运管理, 2009,31(11):1-5
[9] 刘子建. 基于小波理论的国际干散货航运市场周期波动及预测研究[D]. 大连海事大学博士学位论文, 2009
[10] 蒋迪娜. 基于BP滤波的BDI周期性问题研究[J]. 技术经济与管理研究, 2010,(5):23-26
[11] 王磊,李序颖. 基于谱分析的波罗的海干散货运价指数周期研究[J]. 数理统计与管理, 2011,30(6):1051-1059
[12] 林国龙,陈言诚. 基于CF滤波的国际干散货航运市场周期性分析[J]. 上海海事大学学报, 2012,33(3):69-74
[13] 袁群. 国际干散货运输市场波动的影响因素分析与规律研究[J]. 中国水运, 2013,13(3):45-48
[14] 李嘉华. 1985年以来世界航运周期分析[J]. 世界海运, 2013,36(10):1-4
[15] Zeng Q. C., Qu C. R. An Approach for Baltic Dry Index Analysis Based on Empirical Mode Decomposition[J]. Maritime Policy & Management, 2014,41(3):224-240
[16] 黄辉. 航运市场的周期理论和发展趋势预测[J]. 水运管理, 2016,38(2):8-11
[17] Ayenu-Prah A. Y., Attoh-Okine N. O. Comparative Study of Hilbert-Huang Transform, Fourier Transform and Wavelet Transform in Pavement Profile Analysis[J]. Vehicle System Dynamics, 2009,47(4):437-456
[18] Alexandrov T. A Method of Trend Extraction Using Singular Spectrum Analysis[J]. Revstat-Statistical Journal, 2009,7(1):1-22
[19] Huang N. E., Shen Z., Long S. R., et al. The Empirical Mode Decomposition and The Hilbert Spectrum for Nonlinear and Non-stationary Time Series Analysis[J]. Proceedings of the Royal Society A Mathematical Physical & Engineering Sciences, 1998,454(1971):903-995
[20] Dragomiretskity K., Zosso D. Variational Mode Decomposition[J]. IEEE Transactions on Signal Processing, 2014,62(3):531-544
[21] 潘文达,潘思延. 国际航运市场波动机理及应对策略[J]. 综合运输, 2013,(3):36-41
[22] 李瑞华,宋炳良. 国际干散货航运市场影响因素及规律[J]. 上海海事大学学报, 2015,36(3):35-39
[23] Abdoos A. A. A New Intelligent Method Based on Combination of VMD and ELM for Short Term Wind Power Forecasting[J]. Neurocomputing, 2016,203:111-120
[24] Boyd S., Parikh N., Chu E., et al. Distributed Optimization and Statistical Learning via The Alternating Direction Method of Multipliers[J]. Foundations and Trends in Machine Learning, 2010,3(1):1-122
[25] Aneesh C., Kumar S., Hisham P. M., et al. Performance Comparison of Variational Mode Decomposition over Empirical Wavelet Transform for The Classification of Power Quality Disturbances Using Support Vector Machine[J]. Procedia Computer Science, 2015,46:372-380
[26] Zhang X., Yu L., Wang S. Y., et al. Estimating The Impact of Extreme Events on Crude Oil Price: An EMD-based Event Analysis Method[J]. Energy Economics, 2009,31(5):768-778
[27] Wu Z. H., Huang N. E. A Study of Characteristics of White Noise Using The Empirical Model Decomposition Method[J]. Proceedings of the Royal Society of London, 2004,460(2046):1597-1611
[28] Wu Z. H., Huang N. E. Ensemble Empirical Mode Decomposition: A Noise-assisted Data Analysis Method[J]. Advances in Adaptive Data Analysis, 2009,1(1):1-41
[29] 王书平,朱艳云. 基于多尺度分析的小麦价格预测研究[J]. 中国管理科学, 2016,24(5):85-91
[30] 肖志国. 几种水文时间序列周期分析方法的比较研究[D]. 河海大学硕士学位论文, 2006
[31] Lahmiri S. Intraday Stock Price Forecasting Based on Variational Mode Decomposition[J]. Journal of Computational Science, 2016,12:23-27