Paper: arXiv 2506.07928

Authors: Austin Pollok

Abstract

The discrepancy between realized volatility and the market’s view of volatility has been known to predict individual equity options at the monthly horizon. It is not clear how this predictability depends on a forecast’s ability to predict firm-level volatility. We consider this phenomenon at the daily frequency using high-dimensional machine learning models, as well as low-dimensional factor models. We find that marginal improvements to standard forecast error measurements can lead to economically significant gains in portfolio performance. This makes a case for re-imagining the way we train models that are used to construct portfolios.

Complexity vs Empirical Score

  • Math Complexity: 7.5/10
  • Empirical Rigor: 6.0/10 (capped from 8.0: transaction costs not modelled; see penalty flags)
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper employs advanced statistical and machine learning methods for volatility forecasting, supported by formal derivations. It demonstrates strong empirical rigor through an extensive out-of-sample analysis on S&P 500 options data from 1993–2019, evaluating portfolio performance and economic significance.

Research Flowchart

  flowchart TD
  A["Research Goal: Determine if marginal improvements in volatility forecasting error lead to economically significant gains in portfolio construction for equity options."]
  
  subgraph B ["Data & Inputs"]
      B1["High-dimensional machine learning models"]
      B2["Low-dimensional factor models"]
      B3["Realized Variance (benchmark)"]
  end
  
  subgraph C ["Methodology"]
      C1["Daily frequency analysis"]
      C2["Compare model predictions vs. Realized Variance"]
      C3["Measure Forecast Errors"]
  end
  
  subgraph D ["Computational Process"]
      D1["Construct portfolios based on improved forecasts"]
      D2["Evaluate economic significance of gains"]
  end
  
  E["Key Finding: Marginal forecast improvements yield significant economic gains, advocating for re-imagined model training approaches."]

  A --> B
  B --> C
  C --> D
  D --> E

Cited References (77)

  1. A N ew I nterpretation of I nformation R ate (1956)
  2. The K elly C riterion in B lackjack, S ports B etting, and the S tock M arket (2006)
  3. Understanding the K elly C riterion (2012)
  4. Red- B looded R isk (2011)
  5. Beat the D ealer (1966)
  6. Fortune’s F ormula (2006)
  7. The K elly C apital G rowth I nvestment C riterion (2011)
  8. Jump T ype L ' e vy P rocesses (2009)
and 69 more
  1. The C asino G ambler’s G uide (1970)
  2. A F avorable S ide B et in N evada B accarat (1966)
  3. Beat the M arket: A S cientific S tock M arket S ystem. (1967)
  4. Rational D ecision M aking U nder U ncertainty: O bserved B etting P atterns on a B iased C oin (2016)
  5. The Optimum Strategy in Blackjack (1956)
  6. Favorable S trategy for T wenty O ne (1961)
  7. Parametric Portfolio Policies: Exploiting Characteristics in the Cross-Section of Equity Returns (2009)
  8. The Variation of Certain Speculative Prices (1963)
  9. New Methods in Statistical Economics (1963)
  10. Stable Paretian Random Functions and the Multiplicative Variation of Income (1961)
  11. Volatility and Correlation Forecasting (2006)
  12. Option Mispricing around Nontrading Periods (2018)
  13. Sparse Signals in the Cross-Section of Returns (2019)
  14. A Simple Approximate Long-Memory Model of Realized Volatility (2009)
  15. Answering the Skeptics: Yes, Standard Volatility Models Do Provide Accurate Forecasts (1998)
  16. Delta-Hedged Gains and the Negative Market Volatility Risk Premium (2015)
  17. Cross-Section of Option Returns and Volatility (2009)
  18. Data-Based Ranking of Realised Volatility Estimators (2011)
  19. Expected Option Returns (2001)
  20. Volatility Forecast Comparison Using Imperfect Volatility Proxies (2011)
  21. Volatility Forecasting With Range-Based EGARCH Models (2006)
  22. Using Machine Learning to Predict Realized Variance (2020)
  23. Variance Risk Premiums (2008)
  24. Volatility Derivatives (2009)
  25. Leverage Effect, Volatility Feedback, and Self-Exciting Market Disruptions (2017)
  26. Does anything beat 5-minute RV? A comparison of realized measures across multiple asset classes (2015)
  27. Empirical properties of asset returns: stylized facts and statistical issues (2001)
  28. Extracting factors from heteroskedastic asset returns (2001)
  29. Machine learning for regularized survey forecast combination: Partially-egalitarian LASSO and its derivatives (2019)
  30. Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation (1982)
  31. Generalized autoregressive conditional heteroskedasticity (1986)
  32. The Evaluation of Economic Forecasts (1969)
  33. On Black’s Leverage Effect in Firms with No Leverage (2019)
  34. A Theoretical Comparison between Integrated and Realized Volatility (2002)
  35. Why Does Stock Market Volatility Change Over Time? (1989)
  36. Understanding Index Option Returns (2009)
  37. A Nonlinear Factor Analysis of S&P 500 Index Option Returns (2006)
  38. The Pricing of Options and Corporate Liabilities (1973)
  39. Theory of Rational Option Pricing (1973)
  40. Do Option Markets Correctly Price the Probabilities of Movement of the Underlying Asset? (2001)
  41. Recovering Risk Aversion from Option Prices and Realized Returns (2015)
  42. Order Flow and Expected Option Returns (2016)
  43. Option Momentum (2021)
  44. Cross section of option returns and idiosyncratic stock volatility (2013)
  45. Fat-Tailed Kelly (2021)
  46. Credit Variance Risk Premiums (2021)
  47. Characteristic-Sorted Portfolios: Estimation and Inference (2020)
  48. Studies of Stock Price Volatility Changes (1976)
  49. Predicting Excess Stock Returns Out of Sample: Can Anything Beat the Historical Average? (2007)
  50. Anomalies and False Rejections (2020)
  51. Machine Learning in Asset Pricing (2021)
  52. Regression Shrinkage and Selection via the Lasso (1996)
  53. What good is a volatility model? (2001)
  54. Very Noisy Option Prices and Inferences Regarding Option Returns (2021)
  55. The Law of One Price in Equity Volatility Markets (2020)
  56. … and the Cross-Section of Expected Returns (2015)
  57. Implied Stochastic Volatility Models (2020)
  58. Risk and return: Long-run relations, fractional cointegration, and return predictability (2013)
  59. Volatility in Equilibrium: Asymmetries and Dynamic Dependencies (2011)
  60. Expected Stock Returns and Variance Risk Premia (2009)
  61. The distribution of realized stock return volatility (2001)
  62. The Extreme Value Method for Estimating the Variance of the Rate of Return (1980)
  63. On the Estimation of Security Price Volatilities from Historical Data (1980)
  64. Estimating Variance From High, Low and Closing Prices (1991)
  65. Drift‐Independent Volatility Estimation Based on High, Low, Open, and Close Prices (2000)
  66. Kelly Criterion: From a Simple Random Walk to Lévy Processes (2021)
  67. Predicting Out-of-Sample Option Returns from Volatility Risk: Can Anything Beat the Benchmark? (2021)
  68. The common factor in idiosyncratic volatility: Quantitative asset pricing implications (2016)
  69. Attention Induced Trading and Returns: Evidence from Robinhood Users (Forthcoming)

0 of 77 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.