基于去噪和分形的加密货币投资组合模型优化研究

Model optimization of cryptocurrency portfolio based on EMD denoising and DCCA methods

为提高投资效益,本文针对传统投资组合模型的缺陷,结合经验模态分解(EMD)去噪法和多重分形消除趋势交叉相关分析法(MF-DCCA),提出经验模态分解去噪下的多重分形投资组合模型(简称EMD-Mean-MF-DCCA).将新模型应用于极具投机性的加密货币投资组合,结合滚动窗口技术进行样本外检验和分析,实证结果显示:无论加密货币价格处于上升还是下降趋势,EMD-Mean-MF-DCCA相对于其他传统投资组合模型及未去噪的分形投资组合模型,均在盈利能力和夏普比率方面具有明显优化效果,且当加密货币价格大幅下跌时,基于新模型的组合投资策略也具有较好的抵抗风险能力.

The Empirical Mode Decomposition(EMD)denoising and Multifractal Detrended Cross-Correlation Analysis(MF-DCCA)have been combined to address the shortcomings of traditional portfolio models,thus a multiple fractal portfolio model under EMD denoising and MF-DCCA is proposed in this paper.The new model,abbreviated as EMD-Mean-MF-DCCA,is applied to a highly speculative cryptocurrency portfolio,which is then verified by out-of-sample test and analysis with rolling window technique.The results show that whether the cryptocurrency price is on upward or downward trend,the proposed EMD-Mean-MF-DCCA is significantly optimized in terms of profitability and Sharpe ratio compared with traditional portfolio models and non-denoised fractal portfolio models.Moreover,the portfolio investment scheme under the new model has better risk resistance capability when the price of cryptocurrency falls sharply.