Dynamic correlation network analysis of financial asset returns with network clustering

Abstract

In this study, we propose a novel approach to analyze a dynamic correlation network of highly volatile financial asset returns by using a network clustering algorithm to deal with high dimensionality issues. We analyze the dynamic correlation network of selected Japanese stock returns as an empirical study of the correlation dynamics at the market level by applying the proposed method. Two types of network clustering algorithms are employed for the dimensionality reduction. Firstly, several stock groups instead of the existing business sector classification are generated by the hierarchical recursive network clustering of filtered stock returns in order to overcome the high dimensionality problem due to the large number of stocks. The stock returns are then filtered in advance to control for volatility fluctuations that can distort the correlation between stocks. Thus, the correlation network of individual stock returns is transformed into a correlation network of group-based portfolio returns. Secondly, the reduced size of the correlation network is extended to a dynamic one by using a model-based correlation estimation method. A time series of adjacency matrices is created on a daily basis as a dynamic correlation network from the estimation results. Then, the correlation network is summarized into only three representative correlation networks by clustering along the time axis. Some intertemporal comparisons of the dynamic correlation network are conducted by examining the differences between the three sub-period networks. Our dynamic correlation network analysis framework is not limited to stock returns, but can be applied to many other financial and non-financial volatile time series data.

Coarse Graining on Financial Correlation Networks

“…In many quantitative financial models, the correlation matrix of asset returns is based on Pearson's linear correlation. However, when used for fat-tailed financial time series such as stock returns and exchange rates, which have significant volatility changes, the linear correlation may cause some distortion [53,54]. The correlation matrix of unfiltered sample data series with a moving window, as a result, has basic flaws that are generally acknowledged by academics and practitioners.…”

Relationship between Entropy and Dimension of Financial Correlation-Based Network

“…In this article, we use the method of rolling time windows to construct the network. Recently, researchers have estimated the dynamic correlation between time series and constructed networks that can avoid rolling time windows; however, it is difficult to estimate and construct larger networks [ 61 , 62 ]. Therefore, further research should focus on networks based on dynamic correlation.…”

Graphical models for financial time series and portfolio selection

“…As an extension to dynamic dependence networks, Isogai [7] proposed a novel approach to analyze a dynamic correlation network of highly volatile financial asset returns by using network clustering algorithms to mitigate high dimensionality. Two types of network clustering algorithms [5,6] were employed to transform correlation network of individual portfolio returns into a correlation network of group based returns.…”