Newton–Raphson Emulation Network for Highly Efficient Computation of Numerous Implied Volatilities

Author:

Lee Geon,Kim Tae-KyoungORCID,Kim Hyun-Gyoon,Huh JeonggyuORCID

Abstract

In finance, implied volatility is an important indicator that reflects the market situation immediately. Many practitioners estimate volatility by using iteration methods, such as the Newton–Raphson (NR) method. However, if numerous implied volatilities must be computed frequently, the iteration methods easily reach the processing speed limit. Therefore, we emulate the NR method as a network by using PyTorch, a well-known deep learning package, and optimize the network further by using TensorRT, a package for optimizing deep learning models. Comparing the optimized emulation method with the benchmarks, implemented in two popular Python packages, we demonstrate that the emulation network is up to 1000 times faster than the benchmark functions.

Funder

National Research Foundation of Korea

Publisher

MDPI AG

Subject

Finance,Economics and Econometrics,Accounting,Business, Management and Accounting (miscellaneous)

Reference23 articles.

1. Data-driven discovery of pdes in complex datasets;Berg;Journal of Computational Physics,2019

2. The pricing of options and corporate liabilities;Black;Journal of Political Economy,1973

3. A simple formula to compute the implied standard deviation;Brenner;Financial Analysts Journal,1988

4. A generalized simple formula to compute the implied volatility;Chance;Financial Review,1996

5. Chen, Ricky T. Q., Rubanova, Yulia, Bettencourt, Jesse, and Duvenaud, David K. (2022, November 10). Neural Ordinary Differential Equations, in ‘Advances in Neural Information Processing Systems’. Available online: https://papers.nips.cc/paper/2018/hash/69386f6bb1dfed68692a24c8686939b9-Abstract.html.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3