CDS Rate Construction Methods by Machine Learning Techniques

Brummelhuis, Raymond and Luo, Zhongmin (2017): CDS Rate Construction Methods by Machine Learning Techniques.

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.

• Item Type: MPRA Paper
• Language: English
• Keywords: Machine Learning; Counterparty Credit Risk; CDS Proxy Construction; Classification.
• Subjects: B - History of Economic Thought, Methodology, and Heterodox Approaches > B2 - History of Economic Thought since 1925 > B23 - Econometrics ; Quantitative and Mathematical Studies; C - Mathematical and Quantitative Methods > C1 - Econometric and Statistical Methods and Methodology: General; C - Mathematical and Quantitative Methods > C3 - Multiple or Simultaneous Equation Models ; Multiple Variables > C38 - Classification Methods ; Cluster Analysis ; Principal Components ; Factor Models; C - Mathematical and Quantitative Methods > C4 - Econometric and Statistical Methods: Special Topics; C - Mathematical and Quantitative Methods > C4 - Econometric and Statistical Methods: Special Topics > C45 - Neural Networks and Related Topics; C - Mathematical and Quantitative Methods > C5 - Econometric Modeling > C58 - Financial Econometrics; C - Mathematical and Quantitative Methods > C6 - Mathematical Methods ; Programming Models ; Mathematical and Simulation Modeling

References

[1] BCBS, Basel III: A global regulatory framework for more resilient banks and banking systems, Dec.2010 (BIS).

[2] BCBS, Review of the Credit Valuation Adjustment Risk Framework, Jul. 2015, Consultative Document (BIS).

[3] Bloomberg, Credit Default Risk for Public and Private Companies, 2015, Credit Risk Framework, Methodology & Usage.

[4] Berndt, A., Douglas, R., Duffie, D., Ferguson M., Schranz, D., Measure Default Risk Premia from Default Swap Rates and EDFs, BIS Working Papers 173, 2005. Available online at: http://www.bis.org/publ/work173.pdf (accessed 17 April 2017).

[5] Breiman L., Bagging predictors, Machine Learning, 1996, 24(2),123-140.

[6] Breiman, L., Friedman, J., Olshen, R. and Stone, C., Classification and Regression Trees, 1984 (Wadsworth, New York).

[7] Brigo, D., Morini M. and Pallavicini A., Counterparty Credit Risk, Collateral and Funding: With Pricing Cases for All Asset Classes, 2013 (John Wiley and Sons Ltd.).

[8] Brummelhuis, R., Cordoba, A.,Quintanilla, M., Seco, L., Principal Component Value at Risk, Mathematical Finance, 2002, 12(1), 23-43.

[9] Brummelhuis, R. and Luo, Z., No-arbitrage conditions for CDS curves, Working Paper, University of Reims, 2017.

[10] Cai, L., Singenellore R., Bloomberg Credit Default Risk for Private Companies, Bloomberg Professional Service, 2015.

[11] Chourdakis, K., Epperiein E., Jeannin M. and Mcewen J, A crosssection across CVA, 2013, Nomura, Working paper. Available online at: http://www.nomura.com/resources/europe/pdfs/cva-cross-section.pdf (accessed 17 April 2017).

[12] Delgado M., Amorim D., Do we need Hundreds of Classifiers to Solve Real World Classification Problems? Journal of Machine Learning Research, 2014, 15, 3133-3181. 36

[13] Duda, R., Hart, P., Stork D., Pattern Classification, 2nd ed., 2000 (John Wiley and Sons Ltd.).

[14] European Banking Authority, March, 2014, ”Regulatory Technical Standards on Credit Value Adjustment risk for the determination of a proxy spread under Regulation (EU) No 526/2014

[15] EBA Report on CVA under Article 456(2) of Regulation (EU) No 575/2013, 22 Feb. 2015. Available online at: https://www.eba.europa.eu/documents/10180/950548/EBA+Report+on+CVA.pdf (accessed 17 April 2017).

[16] Efron, B., Bootstrap Methods: Another look at the jackknife, Annals of Statistics, 1979, 7, 1-26.

[17] Epanechnikov, V.A., Non-parametric estimation of a multivariate probability density, Theory of Probability and its Applications, 1969, 14(1), 153-158.

[18] Friedman, J. H., Hall, P., On bagging and nonlinear estimation, 2000, Statistics Department Stanford University and CSIRO. Available online at: http://statweb.stanford.edu/ jhf/ftp/bag.pdf (accessed April 18, 2017).

[19] Greene, W., Econometric Analysis, 3rd ed., 1997 (Prentice Hall, New Jersey).

[20] Gregory, J., The XVA Challenge, Counterparty Credit Risk, Funding, Collateral and Capital, 3rdedition, 2015 (John Wiley & Sons Ltd.).

[21] Hassanat A., Abbadi M., Altrawneh G. and Alhasanat A., Solving the Problem of the K Parameter in the KNN Classifier Using an Ensemble Learning Approach, Int. J. of Computer Science and Info Security, 2014, 12, No.8.

[22] Hastie, T., Tisbshirani, R. and Friedman J., The Elements of Statistical Learning, 2-nd edition,2009 (Springer Science+Business Media LLC).

[23] IFRS 13, Fair Value Measurement, IASB and US GAAP publications, 12 May 2011; http://en.wikipedia.org/wiki/Fair_value

[24] Jirina M. and Jirina M., Jr., Classifier Based on Inverted Indexes of Neighbours, Institute of Computer Science Technical Report No. V-1034, Academy of Sciences of the Czech Republic, 2008. Available online at: http://www.marceljirina.cz/files/classifier-based-on-inverted-indexes-ofneighbors.pdf (accessed 18 April 2017).

[25] King, R., Feng, C., and Shutherland, A., Statlog: comparison of classification algorithms on large real-world problems, Applied Artificial Intelligence, 1995, 9(3), 289-333.

[26] Kohavi R., A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection. In JCAI’95 Proceedings of the 14th international joint conference on Artificial intelligence 2, 1137-1143, 1995 (Morgan Kaufmann Publishers Inc., San Francisco).

[27] Longstaff, F., Mithal S. and Neis, E., Corporate yield spreads: Default Risk or Liquidity? J. of Finance, 2005, 60(5), 2213-2253.

[28] R.Merton, On The Pricing of Corporate Debt: The Risk Structure of Interest Rates, J. of Finance, 1974, 29, 449-470.

[29] Quinlan, R., C4.5: Programs for Machine Learning, 1993 (Morgan Kaufmann, San Mateo).

[30] Rebonota, R., Volatility and correlation: the perfect hedger and the fox, 2nd edition, 1999 (John Wiley and Sons Ltd.).

[31] Rish, I., Hellerstein J., Thathachar, J., An analysis of data characteristics that affect na¨ıve Bayes performance, 2001, IBM T.J. Watson Research Center. Available online at:eb.cs.iastate.edu/honavar/rish-bayes.pdf (accessed 18 Apr. 2017).

[32] Wu, X., Kumar, V., Quinlan, J., Ghosh, J., Yang, Q., Motoda, H., McLachlan, G., Ng, A., Liu, B., Yu, P., Zhou, Z., Steinbach, M., Hand, D., Steinberg, D., 2008, Top 10 algorithms in data mining, Knowl. Inf. Syst., 2008, 14(1), 1-137.