Paper: arXiv 2302.08002
Authors: Chen Liu, Chao Wang, Minh-Ngoc Tran, Robert Kohn
Abstract
We propose a new approach to volatility modeling by combining deep learning (LSTM) and realized volatility measures. This LSTM-enhanced realized GARCH framework incorporates and distills modeling advances from financial econometrics, high frequency trading data and deep learning. Bayesian inference via the Sequential Monte Carlo method is employed for statistical inference and forecasting. The new framework can jointly model the returns and realized volatility measures, has an excellent in-sample fit and superior predictive performance compared to several benchmark models, while being able to adapt well to the stylized facts in volatility. The performance of the new framework is tested using a wide range of metrics, from marginal likelihood, volatility forecasting, to tail risk forecasting and option pricing. We report on a comprehensive empirical study using 31 widely traded stock indices over a time period that includes COVID-19 pandemic.
Complexity vs Empirical Score
- Math Complexity: 7.5/10
- Empirical Rigor: 8.5/10
- Quadrant: Holy Grail — high math complexity, high empirical rigor
Why this score: The paper presents a sophisticated synthesis of deep learning (LSTM), financial econometrics (Realized GARCH), and Bayesian inference (Sequential Monte Carlo). Its empirical evaluation is remarkably thorough, testing return and volatility forecasts across 31 global stock indices including market stress periods, though reproducibility is slightly constrained without explicit code repository links.
Research Flowchart
flowchart TD
A[Goal: Enhance Volatility & Tail Risk Forecasting] --> B[Data: 31 Stock Indices including COVID-19 Period]
B --> C[Framework: Combine Realized GARCH & LSTM Neural Networks]
C --> D[Inference: Sequential Monte Carlo / Bayesian Method]
D --> E[Evaluation: Likelihood, Volatility, Tail Risk & Option Pricing]
E --> F[Outcomes: Superior Predictive Accuracy & Adaptability to Stylized Facts]