【Author】 Gezer, Ali
【Source】ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
【影响因子】2.807
【Abstract】Cryptocurrencies, particularly Bitcoin have attracted a lot of attention in the last decades of humanity. Analyzing cryptocurrencies algorithmic differences, chaotic behavior and self-similarity in cryptocurrency metrics might give significant insights for identifying risks and opportunities. Determining the degree of chaos in crypto metrics is critical for understanding complexity, improving prediction capabilities, and supporting decision-making. This study focuses on the analysis of chaos and self-similarity in Bitcoin dynamics for predictability perspective. Return, rate of return and volume quantities in different scales are analyzed with using rescaled range method to reveal the degree of self-similarity. Hurst parameter extracts a comprehensive summary providing information on how current values depend on previous ones to reveal any persistence in Bitcoin metrics. Daily rate of return and return give Hurst degree around 0.64 while they are in between 0.52-0.55 for minutely and hourly based prices. However, an increasing persistence is observed with the increasing time window. Although the largest Lyapunov exponents stay in the positive region for prices and returns of Bitcoin, they are approximately zero for inspected statistics. Periodic characteristics of Bitcoin are also investigated to reveal any dependencies on halving mechanism of Bitcoin. Detailed self-similarity analysis on specific periods shows that bull and bear market seasons don't make any significant effect on the degree of Hurst parameter. Due to nonlinear and unpredictable characteristics of Bitcoin metrics, distribution fittings are applied to characterize BTC return and rate of return. While Wakeby distribution gives best fitting for daily return, Cauchy distribution gives best for hourly returns.
【Keywords】Bitcoin; Self-similarity; Hurst exponent; The largest Lyapunov exponent; R/S; Chaos
【发表时间】2024 2024 OCT 18
【收录时间】2024-10-27
【文献类型】实证数据
【主题类别】
区块链治理-市场治理-市场分析
Zach
这篇论文主要研究了比特币（Bitcoin）动态中的混沌行为和自相似性，以预测其风险和机会。研究人员通过分析比特币的回报率、收益率和交易量等指标，使用重标范围方法（rescaled range method）揭示了自相似性的程度。Hurst参数被用来提取综合信息，以了解当前值如何依赖于前值，从而揭示比特币指标中的任何持续性。此论文的主要研究内容：1. **自相似性分析**：- 使用重标范围方法分析了不同时间尺度上的回报率、收益率和交易量，以揭示自相似性的程度。- Hurst参数表明，对于日回报率和收益率，Hurst程度约为0.64，而对于分钟和小时价格，Hurst程度在0.52-0.55之间。- 随着时间窗口的增加，观察到持续性增加。2. **混沌行为分析**：- 通过计算最大的Lyapunov指数，研究了比特币价格和收益率的混沌行为。 - 尽管最大的Lyapunov指数对于比特币的价格和收益率保持在正区域，但对于检查的统计数据，它们大约为零。3. **周期性特征分析**： - 研究了比特币的周期性特征，以揭示其对比特币减半机制的依赖性。- 详细的自相似性分析表明，牛市和熊市季节对Hurst参数的程度没有显著影响。4. **分布拟合**：- 由于比特币指标的非线性和不可预测性，研究人员应用了分布拟合来描述BTC的回报率和收益率。- Wakeby分布对日回报率提供了最佳拟合，而Cauchy分布对小时回报率提供了最佳拟合。
回复