arXiv：cs.LG· Hans Buehler, Blanka Horvath, Anastasis Kratsios, Magnus Wiese·· 3 小时前
DYSANOS：生成式无套利动态平滑期权曲面模型
DYSANOS Generative Dynamic Smooth Arbitrage-free Non-parametric Option Surfaces
AI 导读
DYSANOS 是首个面向所有行权价与到期日、无静态套利的平滑 SANOS 期权曲面的生成式市场模型，可生成未来数年每日现货与期权价格的完整路径。研究者用 2022-01-03 至 2025-08-29 的 891 个 Option Metrics IvyDB S&P 指数曲面验证其市场重建、稳定性与尾部行为，并给出风险中性密度的数值构造方法。
正文
Abstract:This article presents with DYSANOS the first generative market model for smooth SANOS option surfaces for all strikes and expiries which are free of static arbitrage. Our model is designed to generate entire paths of daily spot and option prices for years in the future.
We present a robust and useful if somewhat simplistic baseline in the form of an AR(1) model. We discuss model setup, data pipeline, and training and investigate market reconstruction, stability, and tail behavior. We illustrate model performance on 891 Option Metrics IvyDB S\&P Index surfaces from 2022-01-03 through to 2025-08-29.
We also demonstrate how to construct numerically a risk-neutral density. As part of this we develop a new test for zero conditional means under a given measure. We show that for 100,000 simulated paths a trading universe of 48 options and spot is numerically free of dynamic arbitrage.
| Subjects: | Mathematical Finance (q-fin.MF); Machine Learning (cs.LG) |
| Cite as: | arXiv:2608.12587 [q-fin.MF] |
| (or arXiv:2608.12587v2 [q-fin.MF] for this version) | |
| https://doi.org/10.48550/arXiv.2608.12587 arXiv-issued DOI via DataCite |
Submission history
From: Hans Buehler [view email]
[v1]
Wed, 12 Aug 2026 21:01:33 UTC (3,808 KB)
[v2]
Wed, 7 Oct 2026 19:46:19 UTC (2,317 KB)
来源：arXiv：cs.LG · arxiv.org