Shocks, Structure, and Signals: Mapping the Evolution of ASEAN-6 Stock Market Networks Before, During, and After COVID-19 Using Graph Neural Networks

This paper explores the evolution of interlinkages among ASEAN-6 equity markets from 2011 to 2024, with a focus on the structural impacts of the COVID-19 crisis. Using a network-based approach—incorporating Pearson correlation, minimum spanning trees (MST), dynamic time warping (DTW), and threshold networks—we observe significant changes in market connectivity across three phases: pre-crisis, crisis, and post-crisis. Findings show a marked contraction in network depth and a reconfiguration of hub nodes during the crisis, followed by partial restoration afterward. To complement the static analysis, a two-layer Graph Convolutional Network (GCN) is employed to classify market regimes, achieving a 65% classification accuracy. Saliency mapping identifies Indonesia and Vietnam as key contributors to regime differentiation, reflecting their significant role in regional contagion. The study highlights the value of combining machine learning and financial network theory to understand market stress transmission and structural adaptation in emerging market systems.