Paper: arXiv 2406.08041

Authors: Francesco Audrino, Jonathan Chassot

Abstract

We investigate the predictive abilities of the heterogeneous autoregressive (HAR) model compared to machine learning (ML) techniques across an unprecedented dataset of 1,455 stocks. Our analysis focuses on the role of fitting schemes, particularly the training window and re-estimation frequency, in determining the HAR model’s performance. Despite extensive hyperparameter tuning, ML models fail to surpass the linear benchmark set by HAR when utilizing a refined fitting approach for the latter. Moreover, the simplicity of HAR allows for an interpretable model with drastically lower computational costs. We assess performance using QLIKE, MSE, and realized utility metrics, finding that HAR consistently outperforms its ML counterparts when both rely solely on realized volatility and VIX as predictors. Our results underscore the importance of a correctly specified fitting scheme. They suggest that properly fitted HAR models provide superior forecasting accuracy, establishing robust guidelines for their practical application and use as a benchmark. This study not only reaffirms the efficacy of the HAR model but also provides a critical perspective on the practical limitations of ML approaches in realized volatility forecasting.

Complexity vs Empirical Score

  • Math Complexity: 4.0/10
  • Empirical Rigor: 8.5/10
  • Quadrant: Street Traders — empirical and applied, lower math complexity

Why this score: The paper relies on straightforward autoregressive and statistical models with minimal advanced mathematics, but demonstrates high empirical rigor through extensive backtesting on a large dataset (1,445 stocks), comprehensive hyperparameter tuning, and robust error metrics (MSE, QLIKE, utility).

Research Flowchart

  flowchart TD
  A["Research Goal<br>Assess HAR vs. ML Models<br>for Volatility Forecasting"] --> B["Dataset<br>1,455 Stocks<br>Realized Vol & VIX"]
  B --> C["Modeling Approaches"]
  C --> D["HAR Model<br>Linear Benchmark"]
  C --> E["Machine Learning<br>Models"]
  D --> F["Optimized Fitting<br>Window & Re-estimation"]
  E --> G["Extensive<br>Hyperparameter Tuning"]
  F --> H{"Performance Evaluation<br>Metrics: QLIKE, MSE, Utility"}
  G --> H
  H --> I["Key Findings<br>HAR Outperforms ML<br>Low Computational Cost<br>Correct Fitting is Crucial"]

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper proposes that a carefully fitted HAR model provides superior forecasting accuracy compared to machine learning methods.

Source sentence
Our analysis focuses on the role of fitting schemes, particularly the training window and re-estimation frequency, in determining the HAR model's performance

Assumes 4

  • HAR models are estimated using a rolling window with regular re‑estimation. model
    Source sentence
    HAR models are typically estimated in a rolling window fashion, where the model is re-estimated at regular intervals using a fixed (or increasing) number of past observations.
  • Transaction costs are proxied by the rolling median bid‑ask spread over the last nine months. execution
    Source sentence
    In this setting, we follow Bollerslev et al. (2018) and use the rolling median of the bid-ask spread over the last nine months as a proxy for transaction costs.
  • Realized utility is interpreted as the percentage of wealth an investor would pay for access to the model’s forecasts. other
    Source sentence
    the values may be interpreted as the percentage of wealth that an investor would be willing to pay in order to access a portfolio that leverages the model’s forecasting capabilities compared to a portfolio that uniquely allocates capital in the risk‑free asset.
  • The analysis uses only realized volatility and VIX as predictors for all models. data
    Source sentence
    HAR consistently outperforms its ML counterparts when both rely solely on realized volatility and VIX as predictors.

Data

  • CRSP U.S. Stock Database · Center for Research in Security Prices market-prices public
    January 2015 to October 2023 · 1,445 U.S. stocks consistently present over nine years
    Source sentence
    We query high-frequency data for a total of 6,061 stocks. Among these, 1,445 stocks remain consistently present throughout the nine years.
  • NYSE Trade and Quote (TAQ) database · New York Stock Exchange order-book commercial
    January 1, 2015 to October 31, 2023 · high‑frequency intraday trade data for the 1,445 selected stocks
    Source sentence
    We source high-frequency intraday trade data for all selected stocks from the TAQ database from January 1, 2015, to October 31, 2023.

Recognised sources: NYSE TAQ

Costs

Modeled Costs are part of the reported headline results.

rolling median of the bid‑ask spread over the last nine months used as proxy

Source sentence
In this setting, we follow Bollerslev et al. (2018) and use the rolling median of the bid-ask spread over the last nine months as a proxy for transaction costs.

Finds 4

  • HAR consistently outperforms ML models in predictive accuracy across QLIKE, MSE, and realized utility metrics. predictive-accuracy
    Source sentence
    HAR consistently outperforms its ML counterparts when both rely solely on realized volatility and VIX as predictors.
  • The HAR model estimated via WLS yields the highest realized utility, even when transaction costs are included, regardless of VIX inclusion. performance
    Source sentence
    the HAR model estimated via WLS markedly outperforms the other models, regardless of whether VIX is included.
  • Larger training windows generally lead to lower RMSE for the HAR model. statistical
    Source sentence
    larger training windows generally lead to lower prediction errors.
  • ML models underperform relative to HAR, with the gap more pronounced for DJIA and Nasdaq‑100 subsets. negative
    Source sentence
    the underperformance of ML models is even more pronounced in these subsets.

Checked by others

Supported by

  • NeuralFactors: A Novel Factor Learning Approach to Generative Modeling of Equities (2024)
    On the question: Does a larger training window length improve model performance (lower RMSE)?
    Compare the findings

    This paper: Larger training windows generally lead to lower RMSE for the HAR model.

    That paper: Increasing training data length improves performance, contradicting the belief that non‑stationarity requires shorter windows.

    Both findings report that increasing the training window length leads to better performance—A observes lower RMSE with larger windows, and B finds longer data improves results, so B supports A.

  • Stock Price Prediction Using a Hybrid LSTM-GNN Model: Integrating Time-Series and Graph-Based Analysis (2025)
    On the question: Does increasing the training window size improve forecasting accuracy and adaptability?
    Compare the findings

    This paper: Larger training windows generally lead to lower RMSE for the HAR model.

    That paper: Expanding window training improved adaptability, mitigated concept drift, and enhanced generalisation.

    Both findings report that larger/expanding windows lower error (RMSE) and enhance generalisation, showing consistent benefits across HAR and LSTM‑GNN approaches.

Code

No repository by the authors found in the paper.

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.

Cited References (46)

  1. Stochastic Volatility and Realized Stochastic Volatility Models (2023) — link
  2. Out-of-sample volatility prediction: Rolling window, expanding window, or both? (2024) — link
  3. Approximation capabilities of multilayer feedforward networks (1991) — link
  4. The Elements of Statistical Learning (2009) — link
  5. Ridge Regression: Biased Estimation for Nonorthogonal Problems (1970)
  6. Random Forests (2001) — link
  7. Greedy function approximation: A gradient boosting machine (2001) — link
  8. Risk Everywhere: Modeling and managing volatility (2018) — link
and 38 more
  1. Bagging Predictors (1996) — link
  2. Forecasting of Realised Volatility with the Random Forests Algorithm (2018) — link
  3. Forecasting and trading high frequency volatility on large indices (2018) — link
  4. Prediction of realized volatility and implied volatility indices using AI and machine learning: A review (2024) — link
  5. Novel hybrid model based on echo state neural network applied to the prediction of stock price return volatility (2021) — link
  6. Lassoing the HAR Model: A Model Selection Perspective on Realized Volatility Dynamics (2016) — link
  7. Complete subset least squares support vector regression (2021) — link
  8. A hybrid approach of adaptive wavelet transform, long short-term memory and ARIMA-GARCH family models for the stock index prediction (2021) — link
  9. Regression Shrinkage and Selection Via the Lasso (1996) — link
  10. Statistical Learning with Sparsity (2015) — link
  11. Good volatility, bad volatility: Signed jumps and the persistence of volatility (2015) — link
  12. A Machine Learning Approach to Volatility Forecasting (2023) — link
  13. Volatility Models and Their Applications (2012)
  14. Realised variance forecasting under Box-Cox transformations (2017) — link
  15. Direct Versus Iterated Multiperiod Volatility Forecasts (2019) — link
  16. Predicting excess stock returns out of sample: Can anything beat the historical average? (2008) — link
  17. HAR Modeling for Realized Volatility Forecasting (2012)
  18. Forecasting global equity market volatilities (2020) — link
  19. Global equity market volatility spillovers: A broader role for the United States (2016) — link
  20. A Practical Guide to harnessing the HAR volatility model (2021) — link
  21. Modeling and forecasting realized volatility (2003) — link
  22. The distribution of exchange rate volatility (2001)
  23. Estimating quadratic variation using realized variance (2002) — link
  24. Realized volatility forecasting: Robustness to measurement errors (2021) — link
  25. Is implied volatility more informative for forecasting realized volatility: An international perspective (2020) — link
  26. Increasing the information content of realized volatility forecasts (2023) — link
  27. Trading and non-trading period realized market volatility: Does it matter for forecasting the volatility of US stocks? (2020) — link
  28. Forecasting realized volatility with machine learning: Panel data perspective (2023) — link
  29. The Model Confidence Set (2011) — link
  30. Volatility Forecasting with Machine Learning and Intraday Commonality (2023) — link
  31. Econometric analysis of realized volatility and its use in estimating stochastic volatility models (2002) — link
  32. Volatility forecast comparison using imperfect volatility proxies (2011) — link
  33. Realized kernels in practice: trades and quotes (2009) — link
  34. The impact of sentiment and attention measures on stock market volatility (2020) — link
  35. Deep Learning (2016) — link
  36. Realized Volatility Forecasting with Neural Networks (2020) — link
  37. A simple approximate long-memory model of realized volatility (2009) — link
  38. Does anything beat 5-minute RV? A comparison of realized measures across multiple asset classes (2015) — link

0 of 46 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.