AI RESEARCH
Do Better Volatility Forecasts Lead to Better Portfolios? Evidence from Graph Neural Networks
arXiv CS.LG
•
ArXi:2605.19278v1 Announce Type: cross This paper tests whether graph neural networks improve realized volatility forecasts and whether those forecasts improve portfolio performance. Using weekly realized volatility for 465 S\&P 500 equities from 2015--2025, Heterogeneous Autoregressive and Long Short-Term Memory baselines are compared against GraphSAGE models built on rolling correlation, sector, and Granger-causal graphs, with and without macro regime features.