Journal of Financial Services Research

, Volume 46, Issue 2, pp 177–193 | Cite as

Ensemble Predictions of Recovery Rates

Article

Abstract

In many domains, the combined opinion of a committee of experts provides better decisions than the judgment of a single expert. This paper shows how to implement a successful ensemble strategy for predicting recovery rates on defaulted debts. Using data from Moody’s Ultimate Recovery Database, it is shown that committees of models derived from the same regression method present better forecasts of recovery rates than a single model. More accurate predictions are observed whether we forecast bond or loan recoveries, and across the entire range of actual recovery values.

Keywords

Recovery rate Loss given default Forecasting Ensemble learning Credit risk 

JEL Classifications

G17 G21 

References

  1. Acharya VA, Bharath ST, Srinivasan A (2007) Does industry-wide distress affect defaulted firms? Evidence from creditor recoveries. J Financ Econ 85:787–821CrossRefGoogle Scholar
  2. Basel Committee on Banking Supervision (2006) International convergence of capital measurement and capital standards. Bank for International SettlementsGoogle Scholar
  3. Bastos JA (2010) Forecasting bank loans loss-given-default. J Bank Financ 34:2510–2517CrossRefGoogle Scholar
  4. Breiman L, Friedman JH, Olshen RA, Stone CJ (1984) Classification and regression trees. Wadworth International Group, Belmont, CaliforniaGoogle Scholar
  5. Breiman L (1996) Bagging predictors. Mach Learn 24:123–140Google Scholar
  6. Caselli S, Gatti S, Querci F (2008) The sensitivity of the loss given default rate to systematic risk: new empirical evidence on bank loans. J Financ Serv Res 34:1–34CrossRefGoogle Scholar
  7. Das SR (2007) Basel II: correlation related issues. J Financ Serv Res 32:17–38CrossRefGoogle Scholar
  8. Dermine J, Neto de Carvalho C (2006) Bank loan losses-given-default: a case study. J Bank Financ 30:1291–1243CrossRefGoogle Scholar
  9. Emery K, Cantor R, Keisman D, Ou S (2007) Moody’s Ultimate Recovery Database. Moody’s Investors ServiceGoogle Scholar
  10. Grunert J, Weber M (2009) Recovery rates of commercial lending: empirical evidence for German companies. J Bank Financ 33:505–513CrossRefGoogle Scholar
  11. Gupton GM, Stein RM (2005) LossCalc V2: dynamic prediction of LGD. Moody’s Investors ServiceGoogle Scholar
  12. Loterman G, Brown I, Martens D, Mues C, Baesens B (2012) Benchmarking regression algorithms for loss given default modeling. Int J Forecast 28:161–170CrossRefGoogle Scholar
  13. Papke LE, Wooldridge JM (1996) Econometric methods for fractional response variables with an application to 401(K) plan participation rates. J Appl Econ 11:619–632CrossRefGoogle Scholar
  14. Varma P, Cantor R (2005) Determinants of recovery rates on defaulted bonds and loans for North American corporate issuers: 1983–2003. J Fixed Income 14:29–44CrossRefGoogle Scholar
  15. Verikas A, Kalsyte Z, Bacauskiene M, Gelzinis A (2010) Hybrid and ensemble-based soft computing techniques in bankruptcy prediction: a survey. Soft Comput 14:995–1010CrossRefGoogle Scholar
  16. Witten IH, Frank E (2005) Data mining: practical machine learning tools and techniques. Morgan Kaufmann PublishersGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  1. 1.CEMAPRE, ISEGTechnical University of LisbonLisboaPortugal

Personalised recommendations