Deep XVAs and the promise of super-fast pricing
Intelligent robots can value complex derivatives such as exotic options in minutes rather than hours
Monte Carlo is synonymous with fast cars, fast money and – in financial circles – a painfully slow way of valuing derivatives.
Now, banks are turning to machine learning in a bid to give their pricing models a turbo-boost.
The technique involves training so-called deep neural networks to approximate the results of Monte Carlo models without having to run millions of simulations.
“The neural network approximates the price of your portfolio when you’re running gigantic, complicated XVA
Only users who have a paid subscription or are part of a corporate subscription are able to print or copy content.
To access these options, along with all other subscription benefits, please contact customer services - www.fx-markets.com/static/contact-us, or view our subscription options here: https://subscriptions.fx-markets.com/subscribe
You are currently unable to print this content. Please contact customer services - www.fx-markets.com/static/contact-us to find out more.
You are currently unable to copy this content. Please contact info@fx-markets.com to find out more.
Copyright Infopro Digital Limited. All rights reserved.
As outlined in our terms and conditions, https://www.infopro-digital.com/terms-and-conditions/subscriptions/ (point 2.4), printing is limited to a single copy.
If you would like to purchase additional rights please email info@fx-markets.com
Copyright Infopro Digital Limited. All rights reserved.
You may share this content using our article tools. As outlined in our terms and conditions, https://www.infopro-digital.com/terms-and-conditions/subscriptions/ (clause 2.4), an Authorised User may only make one copy of the materials for their own personal use. You must also comply with the restrictions in clause 2.5.
If you would like to purchase additional rights please email info@fx-markets.com
More on Tech and data
OMS wars: a new hope for the future
While Jedi powers may be needed to unpick the complexities of some order management workflows, but the dark side of these systems can be defeated by new enhanced solutions
FX data champion outlines transparency push
Stuart Simmons, new head of GFXC working group, wants trading platforms to come clean on how they use client data
Dealer relief at delays to Refinitiv Matching’s tech migration
First phase of replatforming for Swiss spot pairs set to be pushed to mid-2025
Common FX solution needed for mid-tier banks, says SG’s Estrada
e-FX Forum: Fee compression and costly tech spending should encourage dealer collaboration, he says
Data reveals hidden clockwork of FX forwards market
More than 70% of Vanguard’s volumes and nearly half of Pimco’s regularly occur on just four calendar days
Non-banks in RTGSs: greater efficiency or more risk?
Policy-makers and practitioners from central banks in Brazil, Hungary, Israel, Romania, Rwanda and the US share their perspectives
FX automation plans focus on predictive analytics – panel
Panellists suggest banks could explore AI tools for foreign exchange pricing
FX automation: mission incomplete?
This FX Markets webinar delves into the evolution of FX trading desks, the challenges to automating trade workflows, and what vendors and liquidity providers are doing to address this
