Neural Jumps for Option Pricing
Journal of Futures Markets · 2026-09 · 46 (9) · 1660-1679
DOI: 10.1002/fut.70125 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Futures Markets, online erschienen am 28.06.2026. Verfasst von Duosi Zheng und 3 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Motivated by the importance of jump risk in option pricing, we propose a neural jump stochastic differential equation model that integrates neural networks as parameter estimators into a conventional jump‐diffusion model. To address the incompatibility between the backpropagation algorithm and the jump process, we use the Gumbel‐Softmax method to obtain differentiable gradients for jump parameters. We evaluate the model on both simulated data and S&P 500 index options. The results show that incorporating neural jump components substantially improves pricing accuracy relative to existing benchmark models.
Förderung
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Zheng, D., Guo, H., Liu, Y., & Huang, W. (2026). Neural Jumps for Option Pricing. Journal of Futures Markets, 46(9), 1660-1679. https://doi.org/10.1002/fut.70125
Vancouver
Zheng D, Guo H, Liu Y, Huang W. Neural Jumps for Option Pricing. Journal of Futures Markets. 2026;46(9):1660-1679. doi:10.1002/fut.70125
BibTeX
@article{Zheng2026,
author = {Zheng, Duosi and Guo, Hanzhong and Liu, Yanchu and Huang, Wei},
title = {Neural Jumps for Option Pricing},
journal = {Journal of Futures Markets},
year = {2026},
volume = {46},
number = {9},
pages = {1660--1679},
doi = {10.1002/fut.70125}
}
EUVIMED