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

Paper: arXiv 2409.15320

Authors: Zhengyang Chi, Junbin Gao, Chao Wang

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.

Complexity vs Empirical Score

• Math Complexity: 5.5/10
• Empirical Rigor: 7.5/10
• Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper effectively bridges Spatial-Temporal Graph Neural Networks (DCRNN) and classic econometric models (HAR) to solve a real-world market friction: asynchronous trading calendars across global stock indices. Empirical evaluation across 8 global markets demonstrates superior forecasting accuracy, supported by open-source code availability.

Research Flowchart

  flowchart TD
    A["Research Goal: Enhance Global Stock Market Volatility Forecasting"] --> B["Data Inputs: 8 Global Stock Market Indices (All Trading Days)"]
    B --> C["Calculate Volatility Spillover Index"]
    C --> D["Construct Dynamic Graphs of Volatility Networks"]
    D --> E["Train Spatial-Temporal Graph Neural Network (ST-GNN)"]
    E --> F["Key Outcome: Outperforms Baselines in Realized Volatility Forecasting"]