AUTHOR=Purqon Acep , Jamaludin  

TITLE=Community Detection of Dynamic Complex Networks in Stock Markets Using Hybrid Methods (RMT‐CN‐LPAm+ and RMT‐BDM‐SA)

JOURNAL=Frontiers in Physics

VOLUME=Volume 8 - 2020

YEAR=2021

URL=https://www.frontiersin.org/journals/physics/articles/10.3389/fphy.2020.574770

DOI=10.3389/fphy.2020.574770

ISSN=2296-424X

ABSTRACT=A stock market represents a large number of interacting elements leading to more complex hidden interactions.  It is very challenging to find a useful method to reveal more detailed dynamical complex networks.
For the reason, we propose two hybrid methods called RMT-CN-LPAm+ and RMT-BDM-SA (RMT=Random Matrix Theory, CN=Complex Network, LPAm+ =Advanced Label Propagation Algorithm, BDM=Block Diagonal Matrix, SA=Simulated Annealing).
In this study, we investigate the group mapping in S\&P 500 stock market using the two hybrid methods. 
Our results show good performance with each own benefits and strong points. For example, the RMT-CN-LPAM+ successfully identify 6 groups consisting of 485 nodes and 17 isolated nodes with maximum modularity of 0.62 (keeping more group and more maximum modularity). Meanwhile, RMT-BDM-SA provides useful detailed information from matrix decomposition of $C$ into $Cm$ (market-wide), $Cg$ (group), and $Cr$ (noise). Both hybrid methods successfully reveal more detailed community detection of dynamical complex networks in the stock market.