SpotV2Net: Multivariate Intraday Spot Volatility Forecasting via Vol-of-Vol-Informed Graph Attention Networks

34 Pages Posted: 8 Feb 2024

See all articles by Alessio Brini

Alessio Brini

Duke University, Pratt School of Engineering

Giacomo Toscano

University of Florence

Date Written: January 11, 2024

Abstract

This paper introduces SpotV2Net, a multivariate intraday spot volatility forecasting model based on a Graph Attention Network architecture. SpotV2Net represents assets as nodes within a graph and includes non-parametric high-frequency Fourier estimates of the spot volatility and co-volatility as node features. Further, it incorporates Fourier estimates of the spot volatility of volatility and co-volatility of volatility as features for node edges, to capture spillover effects. We test the forecasting accuracy of SpotV2Net in an extensive empirical exercise, conducted with the components of the Dow Jones Industrial Average index. The results we obtain suggest that SpotV2Net yields statistically significant gains in forecasting accuracy, for both single-step and multi-step forecasts, compared to a panel heterogenous auto-regressive model and alternative machine-learning models. To interpret the forecasts produced by SpotV2Net, we employ GNNExplainer (Ying et al., 2019), a model-agnostic interpretability tool, and thereby uncover subgraphs that are critical to a node's predictions.

Keywords: Multivariate spot volatility forecasting, Graph Neural Networks, Graph Attention Networks, spot volatility, spot volatility of volatility, Non-parametric Fourier estimators

JEL Classification: C45, C53

Suggested Citation

Brini, Alessio and Toscano, Giacomo, SpotV2Net: Multivariate Intraday Spot Volatility Forecasting via Vol-of-Vol-Informed Graph Attention Networks (January 11, 2024). Available at SSRN: https://ssrn.com/abstract=4692194 or http://dx.doi.org/10.2139/ssrn.4692194

Alessio Brini (Contact Author)

Duke University, Pratt School of Engineering ( email )

305 Teer Engineering Building
Durham, NC Durham 27708
United States

Giacomo Toscano

University of Florence ( email )

Via delle Pandette, 32
Firenze, 50127
Italy

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
52
Abstract Views
1,476
Rank
715,337
PlumX Metrics