主管:中国科学院
主办:中国优选法统筹法与经济数学研究会
   中国科学院科技战略咨询研究院

中国管理科学 ›› 2026, Vol. 34 ›› Issue (11): 1-13.doi: 10.16381/j.cnki.issn1003-207x.2024.1405cstr: 32146.14.j.cnki.issn1003-207x.2024.1405

• •    下一篇

迁移学习与深度对冲:来自中国股指期权的证据

许清栋1, 姜富伟2,3(), 康杰4, 田汝正5   

  1. 1.北京大学光华管理学院,北京 100871
    2.厦门大学经济学院,福建 厦门 361005
    3.厦门大学宏观经济研究中心,福建 厦门 361005
    4.深圳证券交易所博士后工作站,广东 深圳 518028
    5.中央财经大学中国经济与管理研究院,北京 100081
  • 收稿日期:2024-08-16 修回日期:2026-01-16 出版日期:2026-11-25 发布日期:2026-11-10
  • 通讯作者: 姜富伟 E-mail:fwjiang@xmu.edu.cn
  • 基金资助:
    国家社会科学基金重大项目(25VRC056);国家自然科学基金面上项目(72072193);国家自然科学基金专项项目(72342019);福建省自然科学基金面上项目(2026J001048);计量经济学教育部重点实验室(厦门大学)高性能计算平台的支持项目

Transfer Learning and Deep Hedging: Evidence from Chinese Stock Index Options

Qingdong Xu1, Fuwei Jiang2,3(), Jie Kang4, Ruzheng Tian5   

  1. 1.Guanghua School of Management,Peking University,Beijing 100871,China
    2.School of Economics,Xiamen University,Xiamen 361005,China
    3.Center for Macroeconomic Research,Xiamen University,Xiamen 361005,China
    4.Shenzhen Stock Exchange Postdoctoral Research Station,Shenzhen 518028,China
    4.China Economics and Management Academy,Central University of Finance and Economics,Beijing 100081,China
  • Received:2024-08-16 Revised:2026-01-16 Online:2026-11-25 Published:2026-11-10
  • Contact: Fuwei Jiang E-mail:fwjiang@xmu.edu.cn

摘要:

本文提出了一种结合迁移学习和深度强化学习的智能化期权对冲方法,即迁移学习深度对冲(transfer learning deep hedging,TLDH)算法,并将其应用于中国的股指期权交易市场。通过结合BSM模拟环境的预训练模型和真实交易数据环境微调训练,TLDH算法更好地解决了不完全市场的期权对冲问题。实证结果表明,TLDH算法在我国股指期权市场中的样本外对冲组合夏普比率和尾部风险,均优于其他期权深度对冲算法,并显著优于经典的基于BSM模型的Delta对冲策略。TLDH的对冲效果优势在不同的投资者风险厌恶水平和不同的交易费率环境下均表现出稳健性。本文进一步发现,TLDH相对传统期权对冲方法的优势来源于其能够根据所处的市场环境动态调整策略,例如在交易成本较高时,TLDH智能策略能够主动有选择地降低对冲持仓和调仓幅度,从而在保证对冲效果的同时降低对冲成本。

关键词: 期权对冲, 深度学习, 强化学习, 迁移学习

Abstract:

With the rapid expansion of China’s options market, options have become an increasingly important instrument for risk management in commodity and financial markets. Due to the asymmetric payoff structure of options, sellers face substantial downside risk, making effective hedging strategies essential. Traditional option hedging methods are typically based on mathematical pricing models, most notably the Black–Scholes–Merton (BSM) framework, where the optimal hedge ratio is defined as the option Delta. However, these approaches rely on restrictive assumptions such as constant volatility, continuous price dynamics, and frictionless markets. In practice, transaction costs and market frictions significantly reduce the effectiveness of frequent Delta rebalancing, leaving the problem of optimal hedging in incomplete markets unresolved.Recent advances in deep reinforcement learning (DRL) provide a model-free alternative for option hedging by learning optimal hedging strategies directly from data. Nevertheless, DRL methods suffer from high sample requirements, low data efficiency, and weak tail-risk control, which limit their applicability in real financial markets with scarce data.To address these challenges, a Transfer Learning Deep Hedging (TLDH) framework is proposed that integrates transfer learning with DRL. The core idea is to pretrain a hedging agent in a BSM-based simulated environment, thereby embedding classical hedging knowledge into the agent, and then transfer this knowledge to a real-market environment constructed from historical trading data.The TLDH framework adopts the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm to handle continuous state and action spaces, and incorporates a Long Short-Term Memory (LSTM) structure to capture temporal dependencies in hedge positions and portfolio returns. Empirical analysis is conducted using high-frequency data from the CSI 300 index options market in China. The proposed method is compared with empirical deep hedging (EDH), sim-to-real deep hedging (SRDH), classical Delta hedging, and cost-adjusted Delta hedging strategies.The results show that TLDH consistently achieves higher Sharpe ratios, lower return volatility, and significantly reduced tail risk. These advantages remain robust across different transaction cost levels and investor risk preferences. Overall, it is demonstrated that combining transfer learning with deep reinforcement learning offers an effective and practical solution for option hedging in real-world incomplete markets, and offers valuable insights for both academic research and artificial intelligence applications in financial practice.

Key words: option hedging, deep learning, reinforcement learning, transfer learning

中图分类号: