Graph Neural Networks for Forecasting Multivariate Realized Volatility with Spillover Effects
This addresses volatility forecasting for financial markets, but is incremental as it builds on existing graph neural network approaches with specific methodological tweaks.
The paper tackles forecasting multivariate stock volatility by incorporating spillover effects using graph neural networks, finding that modeling nonlinear spillovers improves short-term (up to one week) forecasting accuracy and that Quasi-likelihood loss substantially outperforms mean squared error.
We present a novel methodology for modeling and forecasting multivariate realized volatilities using customized graph neural networks to incorporate spillover effects across stocks. The proposed model offers the benefits of incorporating spillover effects from multi-hop neighbors, capturing nonlinear relationships, and flexible training with different loss functions. Our empirical findings provide compelling evidence that incorporating spillover effects from multi-hop neighbors alone does not yield a clear advantage in terms of predictive accuracy. However, modeling nonlinear spillover effects enhances the forecasting accuracy of realized volatilities, particularly for short-term horizons of up to one week. Moreover, our results consistently indicate that training with the Quasi-likelihood loss leads to substantial improvements in model performance compared to the commonly-used mean squared error. A comprehensive series of empirical evaluations in alternative settings confirm the robustness of our results.