A general machine learning framework of real-time evaluation for financial derivatives portfolios

Liangliang Zhang (), Ruyan Tian (), Qing Yang () and Tingting Ye ()
Additional contact information
Liangliang Zhang: Shanghai Liangbai Technologies Co., Ltd
Ruyan Tian: Fudan University
Qing Yang: Fudan University
Tingting Ye: University of Maine

Review of Derivatives Research, 2025, vol. 28, issue 2, No 2, 21 pages

Abstract: Abstract In this paper, we develop efficient numerical methods and a general framework, based on AI technologies, to solve for financial derivatives prices and Greeks in a real-time manner. Our methodologies extend the traditional path derivative, likelihood ratio and finite difference approaches, making full use of machine learning techniques, and are able to produce fast and accurate estimates of financial derivative prices and risk-factor sensitivity metrics such as Delta, Gamma, Rho and Vega. The machine learning based computational framework proposed is of both theoretical and practical interest and is readily applicable to day-to-day business. Moreover, we propose a state-of-the-art way for model parameter inference.

Keywords: Real-time derivatives pricing; Machine learning; Path derivative method; Likelihood ratio; Malliavin weighting; Monte Carlo finite difference; Risk neutral no arbitrage pricing; Greeks; Regression pricing; Least-square Monte Carlo (search for similar items in EconPapers)
JEL-codes: C30 (search for similar items in EconPapers)
Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11147-025-09216-5 Abstract (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:kap:revdev:v:28:y:2025:i:2:d:10.1007_s11147-025-09216-5

Ordering information: This journal article can be ordered from
http://www.springer. ... 29/journal/11147/PS2

DOI: 10.1007/s11147-025-09216-5

Access Statistics for this article

Review of Derivatives Research is currently edited by Gurdip Bakshi and Dilip Madan

More articles in Review of Derivatives Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().