Integrated GARCH-GRU in Financial Volatility Forecasting

2025-04-13

AI Summary

This paper addresses the challenge in financial volatility modeling of simultaneously capturing heteroskedasticity, volatility clustering, persistence, and nonlinear dynamics. To this end, we propose a GARCH-GRU hybrid neuron that explicitly incorporates the analytical structure of GARCH(1,1) into the gating mechanism, enabling end-to-end integration of econometric priors with deep representation learning. This design preserves model interpretability while substantially enhancing temporal modeling capability. Empirical evaluation across multiple financial datasets demonstrates that our method achieves significantly lower MSE and MAE than benchmark models—including GARCH-LSTM—while exhibiting superior training efficiency. Moreover, it yields lower Value-at-Risk (VaR) backtesting violation rates, confirming its effectiveness and practical utility for financial risk forecasting and management.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Reasoning under Uncertainty: Relational Probabilistic Models
• Computer Vision: Generative Adversarial Networks (GANs) for Vision

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

In this study, we propose a novel integrated Generalized Autoregressive Conditional Heteroskedasticity-Gated Recurrent Unit (GARCH-GRU) model for financial volatility modeling and forecasting. The model embeds the GARCH(1,1) formulation directly into the GRU cell architecture, yielding a unified recurrent unit that jointly captures both traditional econometric properties and complex temporal dynamics. This hybrid structure leverages the strengths of GARCH in modeling key stylized facts of financial volatility, such as clustering and persistence, while utilizing the GRU's capacity to learn nonlinear dependencies from sequential data. Compared to the GARCH-LSTM counterpart, the GARCH-GRU model demonstrates superior computational efficiency, requiring significantly less training time, while maintaining and improving forecasting accuracy. Empirical evaluation across multiple financial datasets confirms the model's robust outperformance in terms of mean squared error (MSE) and mean absolute error (MAE) relative to a range of benchmarks, including standard neural networks, alternative hybrid architectures, and classical GARCH-type models. As an application, we compute Value-at-Risk (VaR) using the model's volatility forecasts and observe lower violation ratios, further validating the predictive reliability of the proposed framework in practical risk management settings.

Problem

• Proposes GARCH-GRU model for financial volatility forecasting
• Combines econometric properties and temporal dynamics in one unit
• Improves accuracy and efficiency over existing volatility models

Innovation

• Integrated GARCH-GRU for volatility forecasting
• Combines GARCH and GRU in unified architecture
• Superior efficiency and accuracy in predictions