现实市场摩擦下的深度对冲：比特币期权动态对冲的机制条件实证研究
Deep Hedging Under Realistic Market Frictions: A Regime-Conditional Empirical Study of Dynamic Option Hedging on Bitcoin Options
- Visvesvaraya National Institute of Technology, Nagpur（印度理工学院那格浦尔分校）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究基于Deribit五年BTC期权数据，对比经典对冲方法与深度对冲模型，发现经典的Whalley-Wilmott方法在交易成本上优于深度对冲，且结果依赖市场机制，深度对冲未击败经典基准。
AI中文摘要：
经典期权对冲方法如Black-Scholes delta假设存在恒定、无成本的再平衡，这与现实市场不符。深度对冲通过训练神经网络直接处理这些摩擦，现有研究报告了良好结果，但这些对比通常是在模拟价格数据上将深度对冲与无摩擦的经典基准进行比较，这并非公平对比，且无法确定其优势是否真实存在。我们使用Deribit平台2020-2024年五年的实际BTC期权数据进行测试，将Black-Scholes delta、Leland的成本调整对冲、Whalley-Wilmott无交易带这三种经典方法，与三种深度对冲设置进行对比：分别为采用CVaR损失训练的LSTM和前馈网络，部分运行中加入交易频率过高的惩罚项。所有六种策略均面临相同的5个基点交易成本。在2023年9月至2024年12月的11546个测试时段中，Whalley-Wilmott相比每小时再平衡显著降低了交易成本，其交易频率约减少8倍，相比普通BS delta每个时段节省1.79美元（95%置信区间[-2.21, -1.39]，p<0.0001），其损益和尾部风险指标也更优，尽管在该样本量下未达到显著水平。三种深度对冲模型在任何指标上均未击败任何经典基准，且无论惩罚权重在20倍范围内如何变化，所有模型几乎每小时都保持交易。在更平稳的验证期，Whalley-Wilmott的损益优势缩小或消失，但成本优势依然存在，因此结果取决于市场机制。我们认为可能的原因是训练集较小，且所测试的架构缺乏内置的弃权（不执行）机制。这一结果并不亮眼，但很真实：是对迄今为止主要由模拟支持的结论的实际数据检验。
英文摘要：
Classical option-hedging methods like Black-Scholes delta assume constant, free rebalancing, which real markets don't allow. Deep hedging trains a neural network to handle these frictions directly, and prior work reports strong results. But those comparisons usually pit deep hedging against a frictionless classical baseline on simulated price data. That's not a fair fight, and it leaves open whether the advantage is real. We test this using five years of actual BTC options data from Deribit (2020-2024), comparing Black-Scholes delta, Leland's cost-adjusted hedge, and the Whalley-Wilmott no-trade band against three deep hedging setups: an LSTM and a feedforward network, each trained with a CVaR loss and, in some runs, a penalty for trading too often. All six strategies face the same 5 basis point transaction cost. On 11,546 test episodes from September 2023 to December 2024, Whalley-Wilmott cuts transaction costs significantly versus hourly rebalancing, saving $1.79 per episode against plain BS delta (95% CI [-2.21, -1.39], p < 0.0001) by trading about eight times less often. Its P&L and tail-risk numbers are better too, though not quite significant at this sample size. None of the three deep hedging models beat any classical benchmark on any metric, and all kept trading almost every hour regardless of penalty weight, a twenty-fold range barely moved the needle. A calmer validation period shows Whalley-Wilmott's P&L edge shrinks or disappears there while its cost edge holds, so the result depends on market regime. We think the likely causes are a small training set and the lack of any built-in mechanism for sitting still in the architectures tested. Not a flashy result, but an honest one: a real-data check on a claim mostly supported by simulations so far.
