MVA Optimisation with Machine Learning Algorithms

15 Pages Posted: 23 Feb 2017 Last revised: 14 Dec 2017

See all articles by Alexei Kondratyev

Alexei Kondratyev

Abu Dhabi Investment Authority

George Giorgidze

Standard Chartered Bank

Date Written: October 23, 2017

Abstract

MVA is becoming a dominant XVA component in interdealer derivatives trading in the post Margin Reform environment. Unlike FVA which can be either a funding cost or a funding benefit, MVA due to BCBS IOSCO IM is always a cost because of non-rehypothecability of the initial margin posted under the margin rules covering non-centrally cleared derivatives. This prompts dealers to investigate MVA optimisation solutions. The dealers face a complex non-linear optimisation problem: not only MVA is a non-linear function in continuous trade parameters such as tenor and notional, it is also a function of discrete variables such as counterparty and underlying asset. Many standard optimisation algorithms based on the continuity or convexity of the objective function are no longer suitable due to the non-linear and the mixed discrete and continuous nature of the problem. At the same time we observe, mainly on the buy side, increasingly widespread usage of Machine Learning techniques in quantitative finance. This paper is about novel applications of Genetic Algorithm and Particle Swarm Optimisation to the problem of MVA optimisation.

Keywords: MVA, Machine Learning, Genetic Algorithm, Particle Swarm Optimisation, MVA Optimisation

JEL Classification: C61, C63, G13, G15

Suggested Citation

Kondratyev, Alexei and Giorgidze, George, MVA Optimisation with Machine Learning Algorithms (October 23, 2017). Available at SSRN: https://ssrn.com/abstract=2921822 or http://dx.doi.org/10.2139/ssrn.2921822

Alexei Kondratyev (Contact Author)

Abu Dhabi Investment Authority ( email )

Abu Dhabi
United Arab Emirates

George Giorgidze

Standard Chartered Bank ( email )

1 Basinghall Ave
London, EC2V 5DD
United Kingdom
+44 7768 801 905 (Phone)

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
1,130
Abstract Views
4,057
rank
27,459
PlumX Metrics