Cross-Market Asset Allocation and Risk Management under Dynamic Network Structures: Evidence from Monte Carlo Simulations

DOI

10.2991/978-94-6239-774-3_6How to use a DOI?

Keywords

High-Dimensional Covariance; Rolling Graphical LASSO; Portfolio Risk Management; Regime Switching; Sparse Topology

Abstract

High-dimensional portfolio optimization ( N ≈ T ) inherently suffers from ill-conditioned covariance estimates, causing unstable weights and excessive transaction costs. This paper proposes a dynamic risk management framework using the Rolling Graphical LASSO (Glasso) to recover the sparse topology of precision matrices. We evaluate this approach against Sample Covariance and Ledoit-Wolf Shrinkage via a rigorous Monte Carlo simulation of 105 assets, explicitly modeling clustered correlation structures and regime-dependent crisis dynamics. Empirical results demonstrate that Glasso acts as a “risk firewall” during contagion, reducing annualized volatility by approximately 11% (24.86% vs. 27.78%) and, crucially, cutting portfolio turnover by over 80% (0.284 vs. 1.478) compared to the Ledoit-Wolf benchmark. Although strict sparsity constraints result in a conservative Sharpe Ratio (0.193 vs. 0.239), Glasso provides superior cost-efficiency and stability by filtering spurious correlations, effectively balancing the bias-variance trade-off.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Haotong Yang
AU  - Kejun Gao
PY  - 2026
DA  - 2026/09/11
TI  - Cross-Market Asset Allocation and Risk Management under Dynamic Network Structures: Evidence from Monte Carlo Simulations
BT  - Proceedings of the 2026 5th International Conference on Mathematical Statistics and Economic Analysis (MSEA 2026
PB  - Atlantis Press
SP  - 66
EP  - 73
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6239-774-3_6
DO  - 10.2991/978-94-6239-774-3_6
ID  - Yang2026
ER  -