Forecasting Global Stock Volatility with Dynamic Market Graphs

Summary

This paper presents a model for forecasting realized volatility across global stock markets. It represents markets as a changing network, using a volatility spillover index to describe how shocks in one market may propagate to others. A spatial-temporal graph neural network then uses these relationships alongside temporal information to generate forecasts.

The empirical study covers eight global market indices and reports that the proposed model outperforms baseline models across the forecasting scenarios examined. This supports the usefulness of incorporating cross-market connections and trading-day coverage into the forecasting setup. The supplied description does not name the benchmarks, provide forecast metrics, or detail the evaluation period and validation design. The reported advantage therefore applies to the study’s tested indices and scenarios; the abstract alone does not establish performance in other markets or live trading.

Key ideas

• The model forecasts realized volatility for stock markets around the world.
• A volatility spillover index is used to construct a changing graph of market relationships.
• A spatial-temporal graph neural network combines market connections with time-dependent data.
• The empirical analysis includes eight global market indices.
• The model is reported to outperform baselines in the scenarios tested, while broader generalization is not established by the summary.

Tags

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


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









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.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.