Global Stock Market Volatility Forecasting Incorporating Dynamic Graphs and All Trading Days

TL;DR

This paper presents a novel global stock market volatility forecasting model that uses dynamic graphs and includes all trading days, improving accuracy by capturing volatility spillovers across markets.

Contribution

It introduces a spatial-temporal graph neural network that models volatility spillovers and incorporates all trading days for enhanced forecasting accuracy.

Findings

Outperforms baseline models in all scenarios

Effectively captures volatility spillover effects

Utilizes dynamic graph structures for better modeling

Abstract

This paper introduces a global stock market volatility forecasting model that enhances forecasting accuracy and practical utility in real-world financial decision-making by integrating dynamic graph structures and encompassing all active trading days of different stock markets. The model employs a spatial-temporal graph neural network architecture to capture the volatility spillover effect, where shocks in one market spread to others through the interconnective global economy. By calculating the volatility spillover index to depict the volatility network as graphs, the model effectively mirrors the volatility dynamics for the chosen stock market indices. In the empirical analysis covering 8 global market indices, the realized volatility forecasting performance of the proposed model surpasses the baseline models in all forecasting scenarios.