Deep learning for CVA computations of large portfolios of financial derivatives

DOI10.1016/j.amc.2021.126399OpenAlexW3169916788MaRDI QIDQ2244169

Kristoffer Andersson, Cornelis W. Oosterlee

Publication date: 11 November 2021

Published in: Applied Mathematics and Computation (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2010.13843

zbMATH Keywords

WWRexpected shortfalldeep learningBermudan optionsportfolio CVA

Mathematics Subject Classification ID

Mathematical economics (91Bxx) Actuarial science and mathematical finance (91Gxx) Numerical methods for partial differential equations, initial value and time-dependent initial-boundary value problems (65Mxx) Stochastic processes (60Gxx) Numerical methods in Fourier analysis (65Txx)

Related Items

The deep parametric PDE method and applications to option pricing

Uses Software

• Adam

Cites Work

• The stochastic grid bundling method: efficient pricing of Bermudan options and their Greeks
• Pricing early-exercise and discrete barrier options by Fourier-cosine series expansions
• A fast Fourier transform technique for pricing American options under stochastic volatility
• An upwind approach for an American and European option pricing model
• Quadratic Convergence for Valuing American Options Using a Penalty Method
• Improved lower and upper bound algorithms for pricing American options by simulation
• ADI Schemes for Pricing American Options under the Heston Model
• CVA with Wrong-Way Risk in the Presence of Early Exercise
• On the Use of Policy Iteration as an Easy Way of Pricing American Options
• Deep optimal stopping
• A Fourier-Based Valuation Method for Bermudan and Barrier Options under Heston's Model
• Counterparty Credit Risk, Collateral and Funding