Different graph neural network volatility models optimize for forecast MSE, cross-sectional ranking accuracy, and portfolio Sharpe ratio separately, showing these objectives are related but not interchangeable.
Advances in Neural Information Processing Systems , year =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-fin.PM 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Do Better Volatility Forecasts Lead to Better Portfolios? Evidence from Graph Neural Networks
Different graph neural network volatility models optimize for forecast MSE, cross-sectional ranking accuracy, and portfolio Sharpe ratio separately, showing these objectives are related but not interchangeable.