Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Dynamic graph neural networks for enhanced volatility prediction in financial markets

Pulikandala Nithish Kumar, Nneka Umeorah, Alex Alochukwu

TL;DR

A novel approach using Graph Neural Networks (GNNs) to represent global financial markets as dynamic graphs that outperforms traditional GARCH models and other machine learning methods, particularly in short- to mid-term forecasts is proposed.

Abstract

Volatility forecasting is essential for risk management and decision-making in financial markets. Traditional models like Generalized Autoregressive Conditional Heteroskedasticity (GARCH) effectively capture volatility clustering but often fail to model complex, non-linear interdependencies between multiple indices. This paper proposes a novel approach using Graph Neural Networks (GNNs) to represent global financial markets as dynamic graphs. The Temporal Graph Attention Network (Temporal GAT) combines Graph Convolutional Networks (GCNs) and Graph Attention Networks (GATs) to capture the temporal and structural dynamics of volatility spillovers. By utilizing correlation-based and volatility spillover indices, the Temporal GAT constructs directed graphs that enhance the accuracy of volatility predictions. Empirical results from a 15-year study of eight major global indices show that the Temporal GAT outperforms traditional GARCH models and other machine learning methods, particularly in short- to mid-term forecasts. The sensitivity and scenario-based analysis over a range of parameters and hyperparameters further demonstrate the significance of the proposed technique. Hence, this work highlights the potential of GNNs in modeling complex market behaviors, providing valuable insights for financial analysts and investors.

Dynamic graph neural networks for enhanced volatility prediction in financial markets

TL;DR

A novel approach using Graph Neural Networks (GNNs) to represent global financial markets as dynamic graphs that outperforms traditional GARCH models and other machine learning methods, particularly in short- to mid-term forecasts is proposed.

Abstract

Volatility forecasting is essential for risk management and decision-making in financial markets. Traditional models like Generalized Autoregressive Conditional Heteroskedasticity (GARCH) effectively capture volatility clustering but often fail to model complex, non-linear interdependencies between multiple indices. This paper proposes a novel approach using Graph Neural Networks (GNNs) to represent global financial markets as dynamic graphs. The Temporal Graph Attention Network (Temporal GAT) combines Graph Convolutional Networks (GCNs) and Graph Attention Networks (GATs) to capture the temporal and structural dynamics of volatility spillovers. By utilizing correlation-based and volatility spillover indices, the Temporal GAT constructs directed graphs that enhance the accuracy of volatility predictions. Empirical results from a 15-year study of eight major global indices show that the Temporal GAT outperforms traditional GARCH models and other machine learning methods, particularly in short- to mid-term forecasts. The sensitivity and scenario-based analysis over a range of parameters and hyperparameters further demonstrate the significance of the proposed technique. Hence, this work highlights the potential of GNNs in modeling complex market behaviors, providing valuable insights for financial analysts and investors.

Paper Structure

This paper contains 29 sections, 9 equations, 7 figures, 7 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Preliminaries
  4. Volatility and Correlation Analytics
  5. Realized Volatility
  6. Generalized Autoregressive Conditional Heteroskedasticity (GARCH)
  7. Correlation
  8. Volatility Spillover Index
  9. Graph-based Deep Learning Models
  10. Graph Neural Networks (GNNs)
  11. Graph Convolutional Networks (GCNs)
  12. Graph Attention Networks (GATs)
  13. Temporal Graph Attention Network (Temporal GAT)
  14. Methodology
  15. Problem Formulation
  16. ...and 14 more sections

Figures (7)

  • Figure 1: Visualisation of graphs by correlation method; L-R: Training, Validation, Testing
  • Figure 2: Visualisation of graphs by volatility spillover method; L-R: Training, Validation, Testing
  • Figure 3: General design for the Temporal GAT model
  • Figure 4: Realized volatility for 8 selected indices [Left: GSPC, HSI, FTSE, GDAXI; Right: KS11, NSEI, N225, FCHI]
  • Figure 5: Correlation index heatmaps of train, validation and test
  • ...and 2 more figures

Theorems & Definitions (1)

  • Remark 5.1