Paper: arXiv 2604.02743

Authors: Zheqi Fan, Meng Melody Wang, Yifan Ye

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.

Complexity vs Empirical Score

  • Math Complexity: 7.5/10
  • Empirical Rigor: 8.0/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper effectively combines advanced mathematical techniques, specifically rough stochastic volatility and deep learning surrogates, with solid empirical evaluation on options panels. It achieves superior multi-horizon realized volatility forecasts compared to classic benchmark models like Heston, Bates, and VIX.

Research Flowchart

  flowchart TD
    A["Research Question: Do options-driven spot volatility estimates improve HAR-RV volatility forecasting?"] --> B["Data Inputs: Large-scale options panels & High-frequency price data"]
    B --> C["Deep Learning Surrogate: Accelerates rough stochastic volatility model estimation"]
    C --> D["Spot Volatility Extraction: Infer spot vol via iterative two-step approach (Rough Heston vs. Heston/Bates/SVCJ/VIX)"]
    D --> E["HAR-RV Augmentation: Integrate option-implied spot volatility into HAR forecasting models"]
    E --> F["Outcomes: HAR-RV-RHeston outperforms benchmarks across daily to one-month horizons"]

Cited References (138)

  1. Parametric inference and dynamic state recovery from option panels (2015)
  2. Pricing and calibration in the 4-factor path-dependent volatility model — → 2406.02319
  3. The relation between implied and realized volatility (1998)
  4. Deep surrogates for finance: With an application to option pricing (2026)
  5. The VIX , the variance premium and stock market volatility (2014)
  6. Economic policy uncertainty and stock market volatility (2015)
  7. Realized volatility and the influence of market measures on predictability: Analysis of Nord Pool forward electricity data (2011)
  8. Does anything beat 5-minute RV ? A comparison of realized measures across multiple asset classes (2015)
and 130 more
  1. Information gains from using short-dated options for measuring and forecasting volatility (2022)
  2. Merton (1976) implied jump (2025)
  3. Nonparametric Test for Rough Volatility (2025)
  4. Modeling the Implied Volatility Smirk in China : Do Non-Affine Two-Factor Stochastic Volatility Models Work? (2025)
  5. VIX Term Structure in the Rough Heston Model via Markovian Approximation (2026)
  6. Forecasting volatility of the U.S. oil market (2014)
  7. A simple approximate long-memory model of realized volatility (2009)
  8. The Pricing Kernel in Options (2023)
  9. A step closer to the perfect volatility model (2020)
  10. Deep learning volatility: A deep neural network perspective on pricing and calibration in (rough) volatility models (2021)
  11. The impact of jumps in volatility and returns (2003)
  12. Deep calibration of the quadratic rough Heston model (2022)
  13. The quadratic rough Heston model and the joint S&P 500/VIX smile calibration problem (2020)
  14. The risk premia embedded in index options (2015)
  15. Transform analysis and asset pricing for affine jump-diffusions (2000)
  16. A novel pricing method for European options based on Fourier -cosine series expansions (2009)
  17. The price of the smile and variance risk premia (2021)
  18. Specification analysis of option pricing models based on time-changed Lévy processes (2004)
  19. Post-‘87 crash fears in the S&P 500 futures option market (2000)
  20. Inferring volatility dynamics and risk premia from the S&P 500 and VIX markets (2019)
  21. A new closed-form discrete-time option pricing model with stochastic volatility (2024)
  22. Beyond Prompting: An Autonomous Framework for Systematic Factor Investing via Agentic AI (2026)
  23. Valuation of VIX derivatives: Incorporating larger spikes in volatility-of-volatility dynamics (2026)
  24. Deep surrogate for non-affine stochastic volatility option valuation models (2026)
  25. Pricing Models of Volatility Products and Exotic Variance Derivatives (2022)
  26. Variance swap with mean reversion, multifactor stochastic volatility and jumps (2015)
  27. A shot noise model for financial assets (2008)
  28. Statistical properties and economic implications of jump-diffusion processes with shot-noise effects (2011)
  29. Shot-noise processes in finance (2017)
  30. A review on Poisson, Cox, Hawkes , shot-noise Poisson and dynamic contagion process and their compound processes (2021)
  31. Shot-noise cojumps: Exact simulation and option pricing (2023)
  32. An analysis of simultaneous company defaults using a shot noise process (2017)
  33. Option trading and the cross-listed stock returns: Evidence from Chinese A–H shares (2020)
  34. The distribution of realized stock return volatility (2001)
  35. Econometric analysis of realized volatility and its use in estimating stochastic volatility models (2002)
  36. Information contents of intraday SSE 50 ETF options trades (2022)
  37. Option profit and loss attribution and pricing in the Chinese options market (2025)
  38. Perfect hedging in rough Heston models (2018)
  39. 4/2 rough and smooth (2025)
  40. Volatility Is Rough (2018)
  41. Pricing under rough volatility (2016)
  42. Forecasting with option-implied information (2013)
  43. Information in derivatives markets: Forecasting prices with prices (2025)
  44. Automated volatility forecasting (2025)
  45. Time-varying skew in VIX derivatives pricing (2022)
  46. VIX derivatives, hedging and vol-of-vol risk (2020)
  47. Stochastic skew in currency options (2007)
  48. Empirical performance of alternative option pricing models (1997)
  49. A New Model for the Joint Valuation of S&P 500 and VIX Options: Specification Analysis (2024)
  50. Explaining the negative returns to volatility claims: An equilibrium approach (2017)
  51. Volatility modeling and prediction: The role of price impact (2019)
  52. Volatility forecast comparison using imperfect volatility proxies (2011)
  53. Variance swaps with mean reversion and multi-factor variance (2024)
  54. Option pricing under time-varying risk-aversion with applications to risk forecasting (2017)
  55. The shape and term structure of the index option smirk: Why multifactor stochastic volatility models work so well (2009)
  56. Jump and volatility dynamics for the S&P 500: Evidence for infinite-activity jumps with non-affine volatility dynamics from stock and option markets (2017)
  57. The effects of asymmetric volatility and jumps on the pricing of VIX derivatives (2016)
  58. Spike and hike modeling for interest rate derivatives: With an application to SOFR caplets (2024)
  59. Volatility dynamics for the S&P 500: Evidence from realized volatility, daily returns, and option prices (2010)
  60. Double-jump diffusion model for VIX : Evidence from VVIX (2017)
  61. Pricing VXX option with default risk and positive volatility skew (2012)
  62. Continuous-time VIX dynamics: On the role of stochastic volatility of volatility (2013)
  63. Comparing predictive accuracy, twenty years later: A personal perspective on the use and abuse of Diebold-Mariano tests (2015)
  64. The variance process implied in VIX options: Affine vs. non-affine models (2017)
  65. Modelling spikes and pricing swing options in electricity markets (2009)
  66. Equilibruim approach of asset pricing under L 'e vy process (2012)
  67. Analytical solvability and exact simulation in models with affine stochastic volatility and L 'e vy jumps (2023)
  68. The importance of the loss function in option valuation (2004)
  69. A closed-form solution for options with stochastic volatility with applications to bond and currency options (1993)
  70. Atheory ofthetermstructure ofinterest rateS (1985)
  71. Simulation schemes for the Heston model with Poisson conditioning — → 2301.02800
  72. A simple option formula for general jump-diffusion and other exponential L 'e vy processes (2001)
  73. Option valuation using the fast Fourier transform (1999)
  74. Efficient options pricing using the fast Fourier transform (2011)
  75. Valuing futures and options on volatility (1996)
  76. Unspanned Stochastic Volatility and the Pricing of Commodity Derivatives (2009)
  77. How integrated are credit and equity markets? Evidence from index options (2024)
  78. The fine structure of variance: Pricing VIX derivatives in consistent and log- VIX models (2016)
  79. Econometric Models of Option Pricing Errors (1997)
  80. Smiles & smirks: Volatility and leverage by jumps (2022)
  81. GARCH option pricing with volatility derivatives (2023)
  82. Pricing cryptocurrency options (2020)
  83. Breaking VIX at open: Evidence of uncertainty creation and resolution (2021)
  84. Understanding the VIX (2009)
  85. Speculation or hedging?—Options trading prior to FOMC announcements (2022)
  86. Relief rallies after FOMC announcements as a resolution of uncertainty (2018)
  87. Using Intraday Data to Gauge Financial Market Responses to Federal Reserve and ECB Monetary Policy Decisions (2010)
  88. VIX changes and derivative returns on FOMC meeting days (2012)
  89. The Fed’s policy decisions and implied volatility (2011)
  90. Impact of the federal open market committee’s meetings and scheduled macroeconomic news on stock market uncertainty (2004)
  91. Premium for heightened uncertainty: Solving the fomc puzzle (2019)
  92. Financial Modelling with Jump Processes (2003)
  93. Indifference pricing of a life insurance portfolio with risky asset driven by a shot-noise process (2017)
  94. Integrated OU processes and non- Gaussian OU -based stochastic volatility models (2003)
  95. Lifting the Heston model (2019)
  96. Markovian structure of the Volterra Heston model (2019)
  97. Multifactor approximation of rough volatility models (2019)
  98. The characteristic function of rough Heston models (2019)
  99. Options-driven volatility forecasting (2025)
  100. Exact simulation of G amma-driven Ornstein–Uhlenbeck processes with finite and infinite activity jumps (2021)
  101. Joint calibration of VIX and VXX options: Does volatility clustering matter? (2023)
  102. Pricing VIX options with volatility clustering (2020)
  103. Realized variance and market microstructure noise (2006)
  104. Pricing VIX derivatives with infinite-activity jumps (2020)
  105. The valuation of volatility options (2000)
  106. On American VIX options under the generalized 3/2 and 1/2 models (2018)
  107. The mean-reverting 4/2 stochastic volatility model: Properties and financial applications (2020)
  108. Stochastic volatility models and the pricing of VIX options (2013)
  109. Pure jump models for pricing and hedging VIX derivatives (2017)
  110. Pricing VXX options by modeling VIX directly (2022)
  111. Valuation of VIX derivatives (2013)
  112. Pricing VIX options in a stochastic vol-of-vol model (2016)
  113. The price of higher order catastrophe insurance: The case of VIX options (2022)
  114. Fractional Brownian motion as a weak limit of Poisson shot noise processes—with applications to finance (2004)
  115. The matlab ode suite (1997)
  116. Pricing VIX options with volatility clustering (2020)
  117. Volatility-of-volatility risk (2019)
  118. On the right jump tail inferred from the VIX market (2023)
  119. Variance disparity and market frictions (2020)
  120. Comparing predictive accuracy (1995)
  121. A simple, positive semi-definite, heteroskedasticity and autocorrelation consistent covariance matrix (1987)
  122. Modeling and forecasting realized volatility (2003)
  123. Parametric and nonparametric volatility measurement (2010)
  124. Answering the skeptics: Yes, standard volatility models do provide accurate forecasts (1998)
  125. Volatility forecasting with machine learning and intraday commonality (2024)
  126. Forecasting realized volatility with spillover effects: Perspectives from graph neural networks (2025)
  127. Automatic lag selection in covariance matrix estimation (1994)
  128. Markov models for commodity futures: Theory and practice (2010)
  129. Non-Gaussian Ornstein–Uhlenbeck -based models and some of their uses in financial economics (2001)
  130. A practical guide to harnessing the HAR volatility model (2021)

2 of 138 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.