The problem of stock hedging is reconsidered in this paper, where a put option is chosen from a set of available put options to hedge the market risk of a stock. A formula is proposed to determine the probability that the potential loss exceeds a predetermined level of Value-at-Risk, which is used to find the optimal strike price and optimal hedge ratio. The assumptions that the chosen put option finishes in-the-money and the constraint of hedging budget is binding are relaxed in this paper. A hypothesis test is proposed to determine whether the failure rate of hedging strategy is greater than the predetermined level of risk. The performances of the proposed method and the method with those two assumptions are compared through simulations. The results of simulated investigations indicate that the proposed method is much more prudent than the method with those two assumptions.
Enhancing Deep Hedging of Options with Implied Volatility Surface Feedback Information
Department of Finance, HEC Montréal, Canada(蒙特利尔HEC金融系);GERAD and Department of Decision Sciences, HEC Montréal, Canada(GERAD与蒙特利尔HEC决策科学系);Concordia University, Department of Mathematics and Statistics, Canada(康科迪亚大学数学与统计学系)
A deep BSDE approach for the simultaneous pricing and delta-gamma hedging of large portfolios consisting of high-dimensional multi-asset Bermudan options
提出基于离散反射 BSDE、One Step Malliavin 格式与神经网络回归 Monte Carlo 的深度方法,实现高维多资产百慕大期权大型投资组合的联合定价及 delta-gamma 对冲。
Autonomous AI Agents for Option Hedging: Enhancing Financial Stability through Shortfall Aware Reinforcement Learning
Cornell Ann S. Bowers College of Computing and Information Science, Cornell University(康奈尔大学安·索斯·博尔斯计算与信息科学学院);Department of Mathematics, University of Texas at Austin(德克萨斯大学奥斯汀分校数学系);School of Social Sciences, Nanyang Technological University(南洋理工大学社会科学学院);Krieger School of Arts and Sciences, Johns Hopkins University(约翰霍普金斯大学克里eger艺术与科学学院)
本文提出了一种用于长期金融衍生品全球对冲的深度强化学习方法。与Coleman et al.(2007)类似的设置被认为是嵌入在具有棘轮特征的可变年金担保中的回望期权的风险管理。Buehler等人(2019 a)的深度对冲算法被应用于优化神经网络,该神经网络表示具有二次和非二次惩罚的全局对冲策略。据作者所知,这是第一份文件,提出了一个广泛的基准全球政策的长期或有债权与使用各种对冲工具(如基础和标准期权),并与股票跳跃风险的存在。蒙特卡罗实验证明了非二次全局对冲的巨大优越性,因为它同时导致下行风险指标比最佳基准小两到三倍,并获得显著的对冲收益。分析表明,神经网络能够有效地适应他们的对冲决策,以不同的惩罚和程式化的事实,风险资产动态,只有通过模拟表现出这些功能的金融市场。数值结果还表明,非二次的全球政策是显着更适合于长期股权风险,这需要赚取股权风险溢价。