Insights on Time-consistent Deep Hedging under Elicitable Dynamic Risk Measures

2026-09-01

AI Summary

研究通过条件可引导的谱风险度量，在高维篮子期权对冲问题中应用时间一致的深度对冲方法，对比了静态风险度量下的对冲策略。

Abstract

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.

Problem

• deep hedging
• dynamic risk measures
• time-consistency
• high-dimensional problems
• basket option hedging

Innovation

• time-consistent deep hedging
• high-dimensional basket option hedging
• conditional elicitability of spectral risk measures
• scoring function impact