Research on Minimum Variance Delta Hedging Strategy of CSI 300ETF Options

DOI: https://doi.org/10.62517/jse.202511106

Author(s)

Xialin Du, Yajie Wang*

Affiliation(s)

School of Management, Harbin Institute of Technology, Harbin, Heilongjiang, China *Corresponding author.

Abstract

This study constructs Hull & White and neural network-based minimum-variance Delta models, assessing Delta hedging strategies via the Gain metric. Using CSI 300ETF option data (2019/12/23–2023/12/31), we compare LSTM and CNN volatility forecasts and Delta hedging efficacy. Results show the LSTM-based strategy outperforms Black-Scholes and Hull & White approaches, offering optimal risk management for SSE 300ETF options. By integrating volatility dynamics and price reversals, the framework addresses traditional Delta-neutral hedging limitations, advancing practical risk mitigation methodologies.

Keywords

Delta Hedging Strategy; Minimum Variance Delta Hedging; Implied Volatility; Options on CSI 300ETF

References

[1]Cao J, Chen J, Farghadani S, et al. Gamma and Vega hedging using deep distributional reinforcement learning. Frontiers in Artificial Intelligence, 2023, 6: 1129370. [2]Chen Y C, Huang W C. Constructing a stock-price forecast CNN model with gold and crude oil indicators. Applied Soft Computing, 2021, 112: 107760. [3]Crépey S. Delta-hedging vega risk? Quantitative Finance, 2004, 4(5): 559-579. [4]Kirisci M, Cagcag Yolcu O. A new CNN-based model for financial time series: TAIEX and FTSE stocks forecasting. Neural Processing Letters, 2022, 54(4): 3357-3374. [5]Hailiang Zhang, Muhammad Atif Sattar, Haijun Wang. Uncertainty measure: As a proxy for the degree of market imperfection. International Review of Economics & Finance.2024,89:159-171 [6]Yadav A, Jha C K, Sharan A. Optimizing LSTM for time series prediction in Indian stock market. Procedia Computer Science, 2020, 167: 2091-2100. [7]Yang M, Wang J. Adaptability of financial time series prediction based on BiLSTM. Procedia Computer Science, 2022, 199: 18-25. [8]Yong'an Zhang, Binbin Yan, Memon Aasma. A novel deep learning framework: Prediction and analysis of financial time series using CEEMD and LSTM. Expert systems with applications, 2020, 159: 113609. [9]Kun Xia, Xuewei Yanga, Peng Zhu. Delta hedging and volatility-price elasticity: A two-step approach. Journal of Banking and Finance. 2023, 153.106898 [10]Li X, Zhou C, Huang W. Delta-hedged gains of SSE 50 ETF options. Applied Economics [11]Letters, 2022, 29(20): 1864-1867. [12]Lina Song, Wang Yu, Yousheng Tan, Ke Duan. Calculations of fractional derivative option pricing models based on neural network. Journal of Computational and Applied Mathematics. 2024,437 .115462 [13]Udayan Sharma, Madhusudan Karmakar. Measuring minimum variance hedging effectiveness: Traditional vs. sophisticated models. International Review of Financial Analysis. 2023, 87 .102621 [14]Alexander C, Rubinov A, Kalepky M, et al. Regime‐dependent smile‐adjusted delta hedging. Journal of Futures Markets, 2012, 32(3): 203-229. [15]Hull J, White A. Optimal delta hedging for options. Journal of Banking & Finance, 2017, 82: 180-190. [16]Xiaoyijing Chen, Siyuan Liu, Zailin Xu, Mei Yu. Asymmetry in option implied volatility and yield: Evidence from China’s ETF options market Pacific-Basin Finance Journal.2024,85. 102386 [17]Yu-Sheng Lai. Economic evaluation of dynamic hedging strategies using high-frequency data. Finance Research Letters. 2023, 57. 104230