Graph Neural Networks for Forecasting Multivariate Realized Volatility with Spillover Effects

TL;DR

This paper introduces a graph neural network approach for forecasting multivariate realized volatilities, emphasizing nonlinear spillover effects and flexible training methods to improve short-term prediction accuracy.

Contribution

The study develops a novel GNN-based model that captures nonlinear spillover effects and demonstrates the benefits of Quasi-likelihood loss for volatility forecasting.

Findings

Modeling nonlinear spillover effects improves short-term forecast accuracy.

Training with Quasi-likelihood loss outperforms mean squared error.

Multi-hop spillover effects do not significantly enhance predictive accuracy.

Abstract

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.