Dynamical correlations in financial systems

One of the main goals in the field of complex systems is the selection and extraction of relevant and meaningful information about the properties of the underlying system from large datasets. In the last years different methods have been proposed for filtering financial data by extracting a structure of interactions from cross-correlation matrices where only few entries are selected by means of criteria borrowed from network theory. We discuss and compare the stability and robustness of two methods: the Minimum Spanning Tree and the Planar Maximally Filtered Graph. We construct such graphs dynamically by considering running windows of the whole dataset. We study their stability and their edges's persistence and we come to the conclusion that the Planar Maximally Filtered Graph offers a richer and more signi.cant structure with respect to the Minimum Spanning Tree, showing also a stronger stability in the long run.

[1]  Tomaso Aste,et al.  Dynamical networks from correlations , 2006 .

[2]  Stacy Williams,et al.  Detecting a currency's dominance or dependence using foreign exchange network trees. , 2005, Physical review. E, Statistical, nonlinear, and soft matter physics.

[3]  An interest rates cluster analysis , 2004, cond-mat/0401443.

[4]  T. Di Matteo,et al.  Complex networks on hyperbolic surfaces , 2004, cond-mat/0408443.

[5]  J. Gower,et al.  Minimum Spanning Trees and Single Linkage Cluster Analysis , 1969 .

[6]  R. Mantegna.  Hierarchical structure in financial markets , 1998, cond-mat/9802256.

[7]  T. Aste,et al.  Extracting the correlation structure by means of planar embedding , 2005, SPIE Micro + Nano Materials, Devices, and Applications.

[8]  HOW DOES THE EURODOLLAR INTEREST RATE BEHAVE , 2001, cond-mat/0101009.

[9]  Rosario N. Mantegna,et al.  Correlation filtering in financial time series , 2005 .

[10]  Tomaso Aste,et al.  GLASS TRANSITION IN SELF-ORGANIZING CELLULAR PATTERNS , 1999 .

[11]  Tomaso Aste,et al.  Interest rates hierarchical structure , 2005 .

[12]  M Tumminello,et al.  A tool for filtering information in complex systems. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[13]  T. Aste,et al.  Correlation based networks of equity returns sampled at different time horizons , 2007 .

[15]  Bernard Chazelle,et al.  A minimum spanning tree algorithm with inverse-Ackermann type complexity , 2000, JACM.

[16]  T. Aste,et al.  The topological structure of 2D disordered cellular systems , 1997, cond-mat/9709227.

[17]  T. Aste,et al.  Correlation filtering in financial time series (Invited Paper) , 2005, SPIE International Symposium on Fluctuations and Noise.