Do Better Volatility Forecasts Lead to Better Portfolios? Evidence from Graph Neural Networks

By Rylan Wade

Published 2026-05-20

Everscope rating

1686.4

Relevance to quantitative trading

9 / 10

Implementation complexity

7 / 10

Reproducibility

4 / 5

About this paper

Methodology: Graph Neural Network Volatility Forecasting with Portfolio Evaluation. Problem types: Time Series Forecasting, Portfolio Optimization, Ranking, Risk Management, Graph Learning.

arXiv:2605.19278 · Code · Paper rankings

Open the interactive Everscope explorer for full analysis, charts, and paper battles.