可诱导动态风险测度下的时间一致深度对冲方法研究

中文摘要 AI 辅助

我们研究动态风险测度背景下的深度对冲问题，其中序贯决策具有时间一致性。现有文献在该背景下主要考虑低维问题与简单环境动态，而我们处理高维的一篮子期权对冲问题，证明该方法可行且可方便应用于更复杂的状态空间场景。我们利用谱风险测度的条件可诱导性来表示优化目标，探究得分函数的选择如何影响对冲智能体的训练。最后，将时间一致的对冲策略与依赖静态风险测度（导致预承诺）的深度对冲方法进行基准对比。

英文摘要

We study deep hedging in the context of dynamics risk measures, where sequential decisions are time-consistent. Whereas the literature in such context mainly considers low-dimensional problems with simple environment dynamics, we tackle the high-dimensional problem of basket option hedging; we show that the approach is feasible and can be used conveniently in the presence of more complex state spaces. We rely on the conditional elicitability of spectral risk measures to represent the optimization objective. We provide insights on how the choice of scoring function impacts the training of the hedging agent. Lastly, the time-consistent hedging strategies are benchmark against deep hedging approaches relying on static risk measures leading to precommitment.

发表机构

• River Hill High School（里弗山高中）
• Concordia University（康科迪亚大学）

机构由 AI 辅助整理，请以论文原文为准。