On options-driven realized volatility forecasting: Information gains via rough volatility model

TL;DR

This paper investigates whether integrating model-based spot volatility estimators from options data into the HAR model improves realized volatility forecasts, using a deep learning surrogate for efficient estimation.

Contribution

It introduces a novel approach combining rough volatility models with deep learning to enhance volatility prediction accuracy over traditional models.

Findings

Augmented HAR-RV-RHeston model outperforms traditional stochastic volatility models.

Model-based estimators improve forecast accuracy for horizons up to one month.

Deep learning accelerates estimation from large options datasets.

Abstract

We examine whether model-based spot volatility estimators extracted from traded options data enhance the predictive power of the Heterogeneous Autoregressive (HAR) model for realized volatility. Specifically, we infer spot volatility under the rough stochastic volatility model via an iterative two-step approach following Andersen et al. (2015a) and adopt a deep learning surrogate to accelerate model estimation from large-scale options panels. Benchmarked against traditional stochastic volatility models (Heston, Bates, SVCJ) and the VIX index, our results demonstrate that the augmented HAR-RV-RHeston model improves daily realized volatility forecasting accuracy and sustains superior performance across horizons up to one month.