Neural Networks for Credit Risk and xVA in a Front Office Pricing Environment
(2022) In Master’s Theses in Mathematical Sciences FMSM01 20221Mathematical Statistics
- Abstract
- We present a data-driven proof of concept model capable of reproducing expected counterparty credit exposures from market and trade data. The model has its greatest advantages in quick single-contract exposure evaluations that could be used in front office xVA solutions. The data was generated using short rates from the Hull-White One-Factor model. The best performance was obtained from a GRU neural network with two recurrent layers, which with adequate accuracy could reproduce the exposure profile for an interest rate swap contract. Errors were comparable to those expected from a Monte Carlo simulation with 5K paths. With regards to computational efficiency, the proposed model showed great potential in outperforming traditional numerical... (More)
- We present a data-driven proof of concept model capable of reproducing expected counterparty credit exposures from market and trade data. The model has its greatest advantages in quick single-contract exposure evaluations that could be used in front office xVA solutions. The data was generated using short rates from the Hull-White One-Factor model. The best performance was obtained from a GRU neural network with two recurrent layers, which with adequate accuracy could reproduce the exposure profile for an interest rate swap contract. Errors were comparable to those expected from a Monte Carlo simulation with 5K paths. With regards to computational efficiency, the proposed model showed great potential in outperforming traditional numerical methods. Further development and calibration to actual market data is required for the model to be applicable in the industry. The proposed architectures may then prove useful, especially for contracts with high-rated counterparties, traded in a normal and liquid market. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/9087036
- author
- Frodé, Isabelle LU and Sambergs, Viktor LU
- supervisor
- organization
- course
- FMSM01 20221
- year
- 2022
- type
- H2 - Master's Degree (Two Years)
- subject
- keywords
- xVA, CVA, OTC, Counterparty Credit Risk, Interest Rate Swaps, Hull-White Model, Machine Learning, Artificial Neural Networks, Gated Recurrent Units
- publication/series
- Master’s Theses in Mathematical Sciences
- report number
- LUTFMS-3441-2022
- ISSN
- 1404-6342
- other publication id
- 2022:E31
- language
- English
- id
- 9087036
- date added to LUP
- 2022-06-14 09:06:20
- date last changed
- 2022-06-14 09:06:20
@misc{9087036, abstract = {{We present a data-driven proof of concept model capable of reproducing expected counterparty credit exposures from market and trade data. The model has its greatest advantages in quick single-contract exposure evaluations that could be used in front office xVA solutions. The data was generated using short rates from the Hull-White One-Factor model. The best performance was obtained from a GRU neural network with two recurrent layers, which with adequate accuracy could reproduce the exposure profile for an interest rate swap contract. Errors were comparable to those expected from a Monte Carlo simulation with 5K paths. With regards to computational efficiency, the proposed model showed great potential in outperforming traditional numerical methods. Further development and calibration to actual market data is required for the model to be applicable in the industry. The proposed architectures may then prove useful, especially for contracts with high-rated counterparties, traded in a normal and liquid market.}}, author = {{Frodé, Isabelle and Sambergs, Viktor}}, issn = {{1404-6342}}, language = {{eng}}, note = {{Student Paper}}, series = {{Master’s Theses in Mathematical Sciences}}, title = {{Neural Networks for Credit Risk and xVA in a Front Office Pricing Environment}}, year = {{2022}}, }