论文部分内容阅读
将生物信息学中的序列比对方法引入金融时间序列分析,可以捕获变量的大尺度特征,抑制噪声,并能从不同角度挖掘系统的隐含模式,且无需过度的前提假设。本文在已有序列比对方法的基础上,提出了两种用于金融序列比对的打分矩阵的构造方法,即相似度导向型矩阵和目的导向型矩阵,前者侧重于反映历史数据信息,可用于发现序列的对应模式,后者考虑对序列进行比对的目的,可用于提取序列的特征片段。应用该方法,本文对上证综指和深证成指的涨跌特征及其相关性进行了实证研究,得到了良好的研究效果,印证了将该方法引入金融领域分析的可行性和有效性。
By introducing the method of sequence alignment into the analysis of financial time series, we can capture the large-scale features of variables, restrain the noise, and excavate the implicit patterns of the system from different perspectives without any excessive assumptions. Based on the existing methods of sequence alignment, this paper proposes two construction methods of scoring matrix for financial sequence alignment, namely similarity-oriented matrix and destination-oriented matrix. The former focuses on reflecting the historical data and is available For the purpose of finding the corresponding patterns of sequences, the latter considers the purpose of aligning the sequences and can be used to extract the characteristic fragments of the sequences. Applying this method, this paper conducts an empirical research on the up and down characteristics of Shanghai Composite Index and the Shenzhen Component Index, and obtains good research results. It proves the feasibility and effectiveness of introducing this method into the financial field analysis.