Zero-shot time series foundation models largely fail to beat econometric benchmarks for realized volatility forecasting, with only TTM achieving a narrow, calibration-driven edge.
and Bollerslev, Tim , title =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
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.
citing papers explorer
-
Forecasting Realized Volatility with Time Series Foundation Models: A Comparison with Econometric Benchmarks
Zero-shot time series foundation models largely fail to beat econometric benchmarks for realized volatility forecasting, with only TTM achieving a narrow, calibration-driven edge.
-
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.