CDS Proxy Construction via Machine Learning Techniques Part I: Methodology and Results
Journal of Financial Data Science, Vol. 1 No. 2, 2019
Posted: 6 Mar 2019 Last revised: 15 May 2019
Date Written: November 5, 2018
To price and risk-manage OTC derivatives, financial institutions have to estimate counterparty default risks based on liquidly quoted CDS rates. For the vast majority of counterparties, liquid CDS quotes are not available and proxy CDS-rates need to be constructed. Existing methods ignore counterparty-specific default risks and can lead to arbitrage. The authors propose to construct CDS proxy-rates by Machine Learning techniques to associate liquidly quoted CDS Proxy Names to illiquid ones on the basis of observable financial feature variables. A benchmarking exercise shows that the proposed method leads to significantly smaller estimation errors than existing ones. The authors tested 126 classifiers coming from the 8 most popular algorithms, rank-ordered performances and investigated performance variations amongst and within the classifiers. In Part I, the authors present the methodology, review the different Machine Learning techniques and report on Cross-classifier performance. In Part II, they focus on parametrization and Intra-classifier performances, investigate correlation effects and perform a benchmarking exercise. This is a first systematic study of CDS Proxy Construction by Machine Learning Techniques and a first classifier comparison study entirely based on financial market data. The techniques should be of interest for financial institutions seeking proxies for CDS rates or other financial variables.
Keywords: CDS Proxy Construction, Counterparty Credit Risk, Machine Learning, Classification
JEL Classification: C4, C45, C63
Suggested Citation: Suggested Citation