A study on the bursting point of Bitcoin based on the BSADF and LPPLS methods

被引:22
|
作者
Yao, Can-Zhong [1 ]
Li, Hong-Yu [1 ]
机构
[1] South China Univ Technol, Sch Econ & Finance, Guangzhou 510006, Peoples R China
关键词
Bitcoin; Bubble periods; LPPLS; GSADF;
D O I
10.1016/j.najef.2020.101280
中图分类号
F8 [财政、金融];
学科分类号
0202 ;
摘要
We aim to reveal the characteristics and mechanism of the Bitcoin bubble in 2019. First, we identify the period during which two important Bitcoin bubbles occurred based on the generalized supremum augmented Dickey-Fuller (GSADF) method. There are two significant bubble cycles. The first bubble lasted approximately 26 days from November 25, 2017, to December 21, 2017, while the second bubble lasted approximately one week from June 22 to June 29, 2019. The occurrence of the first bubble was related to the considerable expansion of initial coin offerings (ICOs) in 2017, while the formation of the second bubble was affected by the release of Libra. Second, as the GSADF method cannot be used to accurately infer the time at which a bubble bursts, we employ the log-periodic power law singularity (LPPLS) model for this purpose. We verify that the LPPLS method can not only infer the timing of a bubble burst but also shows stable results. Finally, we demonstrate the implications of the 2019 bubble. During the 2019 bubble, due to the increased supervision of European and American governments and the impact of hedging assets, the bubble's duration was shorter, and the positive feedback mechanism was not as strong as that of the 2017 bubble. In addition, the oscillating frequency of the bubble in 2019 was low and unstable, which means that it would be more beneficial for investors to hold the currency for a long time.
引用
收藏
页数:10
相关论文
共 50 条
  • [21] EDGE-BASED SMOOTHED POINT INTERPOLATION METHODS
    Liu, G. R.
    Zhang, G. Y.
    INTERNATIONAL JOURNAL OF COMPUTATIONAL METHODS, 2008, 5 (04) : 621 - 646
  • [22] CLASSIFICATION OF LiDAR DATA WITH POINT BASED CLASSIFICATION METHODS
    Yastikli, N.
    Cetin, Z.
    XXIII ISPRS CONGRESS, COMMISSION III, 2016, 41 (B3): : 441 - 445
  • [23] Interior point based continuous methods for linear programming
    Liao, Li-Zhi
    2010 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS IJCNN 2010, 2010,
  • [24] Comparative Study of Two Methods of Tracking Point Selection
    Xiao Yong
    Wang Wen-peng
    Fan Qing-hui
    PROCEEDINGS OF 2014 3RD ASIA-PACIFIC CONFERENCE ON ANTENNAS AND PROPAGATION (APCAP 2014), 2014, : 1355 - 1358
  • [25] Point Cloud Visualization Methods: a Study on Subjective Preferences
    Dumic, Emil
    Battisti, Federica
    Carli, Marco
    da Silva Cruz, Luis A.
    28TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2020), 2021, : 595 - 599
  • [26] Point-to-point FTR obligations auction based on AC-OPF by interior point methods
    Hua, Ke
    Xie, Kai
    Guo, Zhizhong
    2006 IEEE/PES TRANSMISSION & DISTRIBUTION CONFERENCE & EXPOSITION: LATIN AMERICA, VOLS 1-3, 2006, : 359 - +
  • [27] A Study of Bitcoin-Based Intraday Volatility Forecasting for Cross-Market Spreads
    Yang, Longguang
    Hou, Fengshuang
    Shi, Huihong
    EMERGING MARKETS FINANCE AND TRADE, 2023, 59 (14) : 3941 - 3951
  • [28] Long range dependence in the Bitcoin market: A study based on high-frequency data
    Zargar, Faisal Nazir
    Kumar, Dilip
    PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2019, 515 : 625 - 640
  • [29] Comparative study of Bitcoin price prediction using WaveNets, Recurrent Neural Networks and other Machine Learning Methods
    Felizardo, Leonardo
    Oliveira, Roberth
    Del-Moral-Hernandez, Emilio
    Cozman, Fabio
    2019 6TH INTERNATIONAL CONFERENCE ON BEHAVIORAL, ECONOMIC AND SOCIO-CULTURAL COMPUTING (BESC 2019), 2019,
  • [30] A comparative study of maximum power point tracking methods for a photovoltaic-based water pumping system
    Kumar, Bhavnesh
    Chauhan, Yogesh K.
    Shrivastava, Vivek
    INTERNATIONAL JOURNAL OF SUSTAINABLE ENERGY, 2014, 33 (04) : 797 - 810