CDS Rate Construction Methods by Machine Learning Techniques

51 Pages Posted: 15 May 2017 Last revised: 23 Mar 2018

Raymond Brummelhuis

University of Reims Champagne-Ardenne

Zhongmin Luo

Birkbeck, University of London

Date Written: May 12, 2017

Abstract

Regulators require financial institutions to estimate counterparty default risks from liquid CDS quotes for the valuation and risk management of OTC derivatives. However, the vast majority of counterparties do not have liquid CDS quotes and need proxy CDS rates. Existing methods cannot account for counterparty-specific default risks; we propose to construct proxy CDS rates by associating to illiquid counterparty liquid CDS Proxy based on Machine Learning Techniques. After testing 156 classifiers from 8 most popular classifier families, we found that some classifiers achieve highly satisfactory accuracy rates. Furthermore, we have rank-ordered the performances and investigated performance variations amongst and within the 8 classifier families. This paper is, to the best of our knowledge, the first systematic study of CDS Proxy construction by Machine Learning techniques, and the first systematic classifier comparison study based entirely on financial market data. Its findings both confirm and contrast existing classifier performance literature. Given the typically highly correlated nature of financial data, we investigated the impact of correlation on classifier performance. The techniques used in this paper should be of interest for financial institutions seeking a CDS Proxy method, and can serve for proxy construction for other financial variables. Some directions for future research are indicated.

Thanks for the feedbacks from participants at the conferences/seminars; please feel free to check out some of the updated presentation slides: 1. Departmental Seminar of Statistics at London School of Economics, London, Mar. 2017; 2. New Methods, Perspectives and Approaches Seminar at Bank of England, London, Oct. 2017; 3. Machine Learning and AI in Quantitative Finance 2017 Conference, London, Nov. 2017; 4. Machine Learning and AI in Quantitative Finance 2018 Conference, London, Mar. 2018; 5. Call for Paper 2018 Winner of Risk's Quant Summit Europe Conference, London, Mar 2018.

Keywords: Machine Learning, Counterparty Credit Risk, CDS Proxy Method, Classification

JEL Classification: C4, C45, C55, C58, C63, G01

Suggested Citation

Brummelhuis, Raymond and Luo, Zhongmin, CDS Rate Construction Methods by Machine Learning Techniques (May 12, 2017). Available at SSRN: https://ssrn.com/abstract=2967184 or http://dx.doi.org/10.2139/ssrn.2967184

Raymond Brummelhuis

University of Reims Champagne-Ardenne ( email )

51096 Reims Cedex
France

Zhongmin Luo (Contact Author)

Birkbeck, University of London ( email )

Malet Street
London, London WC1
United Kingdom

Register to save articles to
your library

Register

Paper statistics

Downloads
3,697
rank
2,251
Abstract Views
12,365
PlumX