基于XGBoost和HAR-RV的已实现波动率预测
Realized Volatility Prediction Based on XGBoost and HAR-RV
摘要: 本研究构建了基于极端梯度提升(XGBoost)和已实现波动率异质自回归(HAR-RV)的混合模型，采用沪深300指数的五分钟价格数据，选取已实现波动率的历史值、市场交易指标和技术指标作为特征进行预测，根据XGBoost重要性评分，使用递归特征消除法进行特征选择。实验结果表明，我们所提出的混合模型预测效果优于目前主流应用的单一模型，XGBoost递归特征消除起到了优化特征子集的作用。本研究旨在为金融市场的波动率预测提供新的视角，并为投资者和风险管理者提供一种有效的工具。
Abstract: This study develops a hybrid model based on Extreme Gradient Boosting (XGBoost) and Heterogeneous Autoregression of Realized Volatility (HAR-RV), employing five-minute price data from the CSI 300 Index. We select historical values of realized volatility, trading indicators, and technical indicators as features for prediction. Feature selection is conducted using Recursive Feature Elimination based on XGBoost importance scores. The experimental results indicate that the hybrid model we propose has superior predictive performance compared to the currently mainstream single models, and the XGBoost recursive feature elimination effectively optimizes the subset of features. This research aims to provide a fresh perspective on financial market volatility prediction and to offer investors and risk managers a potent tool.
文章引用：杜宇萌, 张凌聪. 基于XGBoost和HAR-RV的已实现波动率预测[J]. 计算机科学与应用, 2025, 15(2): 44-56. https://doi.org/10.12677/csa.2025.152032

参考文献

[1] Engle, R.F. (1982) Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation. Econometrica, 50, 987-1007. [Google Scholar] [CrossRef] 
[2] Bollerslev, T. (1986) Generalized Autoregressive Conditional Heteroskedasticity. Journal of Econometrics, 31, 307-327. [Google Scholar] [CrossRef] 
[3] Andersen, T.G. and Bollerslev, T. (1998) Answering the Skeptics: Yes, Standard Volatility Models Do Provide Accurate Forecasts. International Economic Review, 39, 885-905. [Google Scholar] [CrossRef] 
[4] Corsi, F. (2008) A Simple Approximate Long-Memory Model of Realized Volatility. Journal of Financial Econometrics, 7, 174-196. [Google Scholar] [CrossRef] 
[5] 胡越, 王桑原, 覃浩恒, 等. 基于双重XGBoost模型的农产品期货波动率预测——以玉米期货为例[J]. 系统管理学报, 2023, 32(2): 332-342.
[6] Tissaoui, K., Zaghdoudi, T., Hakimi, A. and Nsaibi, M. (2022) Do Gas Price and Uncertainty Indices Forecast Crude Oil Prices? Fresh Evidence through XGBoost Modeling. Computational Economics, 62, 663-687. [Google Scholar] [CrossRef] [PubMed]
[7] Kristjanpoller, W. and Minutolo, M.C. (2018) A Hybrid Volatility Forecasting Framework Integrating GARCH, Artificial Neural Network, Technical Analysis and Principal Components Analysis. Expert Systems with Applications, 109, 1-11. [Google Scholar] [CrossRef] 
[8] Wang, Y. and Guo, Y. (2020) Forecasting Method of Stock Market Volatility in Time Series Data Based on Mixed Model of ARIMA and Xgboost. China Communications, 17, 205-221. [Google Scholar] [CrossRef] 
[9] Aras, S. (2021) Stacking Hybrid GARCH Models for Forecasting Bitcoin Volatility. Expert Systems with Applications, 174, Article ID: 114747. [Google Scholar] [CrossRef] 
[10] 邱冬阳, 丁玲, 何一夫. 基于高频数据和EN-LSTM的黄金期货短期波动率预测[J]. 运筹与管理, 2024, 33(3): 184-190
[11] Dai, H., Huang, G., Zeng, H. and Zhou, F. (2022) PM2.5 Volatility Prediction by Xgboost-MLP Based on GARCH Models. Journal of Cleaner Production, 356, Article ID: 131898. [Google Scholar] [CrossRef] 
[12] Andersen, T.G., Bollerslev, T., Diebold, F.X. and Labys, P. (2003) Modeling and Forecasting Realized Volatility. Econometrica, 71, 579-625. [Google Scholar] [CrossRef] 
[13] Barndorff-Nielsen, O.E. and Shephard, N. (2002) Econometric Analysis of Realized Volatility and Its Use in Estimating Stochastic Volatility Models. Journal of the Royal Statistical Society Series B: Statistical Methodology, 64, 253-280. [Google Scholar] [CrossRef] 
[14] Müller, U.A., Dacorogna, M.M., Davé, R.D., Olsen, R.B., Pictet, O.V. and von Weizsäcker, J.E. (1997) Volatilities of Different Time Resolutions—Analyzing the Dynamics of Market Components. Journal of Empirical Finance, 4, 213-239. [Google Scholar] [CrossRef] 
[15] Chen, T. and Guestrin, C. (2016) XGBoost. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, 13-17 August 2016, 785-794. [Google Scholar] [CrossRef] 
[16] Darst, B.F., Malecki, K.C. and Engelman, C.D. (2018) Using Recursive Feature Elimination in Random Forest to Account for Correlated Variables in High Dimensional Data. BMC Genetics, 19, Article No. 65. [Google Scholar] [CrossRef] [PubMed]
[17] 吴辰文, 梁靖涵, 王伟, 等. 基于递归特征消除方法的随机森林算法[J]. 统计与决策, 2017(21): 60-63.