Skip to main content

Distributed Calculation Credit Portfolio Models

Abstract

Credit portfolio models are—besides rating models—the most important tools to measure and manage credit risks. The technological advancement in cheap and size-adaptable computational power enables fast and efficient new model implementation patterns for Monte-Carlo-based credit portfolio models. As an illustrative example, the well-accepted CreditMetrics model is implemented on a Hadoop cluster.

Keywords

  • Hadoop
  • Spark
  • CreditMetrics
  • Distributed calculation

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-78829-2_7
  • Chapter length: 16 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   69.99
Price excludes VAT (USA)
  • ISBN: 978-3-030-78829-2
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Hardcover Book
USD   89.99
Price excludes VAT (USA)
Fig. 1

(© ifb SE)

Fig. 2

(© ifb SE)

Fig. 3

(© ifb SE)

Fig. 4

(© ifb SE)

Fig. 5

(© ifb SE)

Fig. 6

(© ifb SE)

Fig. 7

(© ifb SE)

Fig. 8

(© ifb SE)

Fig. 9

(© ifb SE)

Fig. 10

(© ifb SE)

Fig. 11

(© ifb SE)

Fig. 12

(© ifb SE)

Notes

  1. 1.

    See Gupton et al. (1997).

  2. 2.

    See Kealhofer (1998).

  3. 3.

    See Wilde (1997).

  4. 4.

    See Wilson, Portfolio credit risk (I) (1997) and Wilson, Portfolio credit risk (II) (1997), The German Savings Banks Association (DSGV) has developed a specific model variant.

  5. 5.

    CreditRisk+ is a closed formula model, which is a solved algorithm (e.g. by using Fourier transformation).

  6. 6.

    The convergence of Monte Carlo simulation is a widely discussed topic in science (see xx).

  7. 7.

    In practical implementations, only in rare situations do more than three factor-loadings not equal zero. These three main factors usually cover the main impact of the economy on the client. In some implementations, the factor-loadings are restricted to one factor (representing the whole economy, e.g. GDP).

  8. 8.

    Value at risk (see Jorion 2006).

  9. 9.

    Expected shortfall (see McNeil et al. 2005).

  10. 10.

    See Sect. 2.3.1.

  11. 11.

    One common application is the calculation of risk contributions of a single client to the portfolio VaR.

  12. 12.

    Worker node is a common expression in cluster architectures like Hadoop and describes the server (node) doing the bulk of the work (in terms of data or computational power); the counterpart is the master node, which is responsible for overseeing the key operations.

  13. 13.

    Some of the more technical improvements by Spark parameters are discussed in the following section (Sect. 3.3).

  14. 14.

    CDH 6.1.1: CDH 6.1.1 Release Notes | 6.x | Cloudera Documentation.

Literature

  • Crouhy, M., D. Galai, R. Mark. 2000. “A Comparative Analyis of Current Credit Risk Models.” Journal of Banking, Finance 24: 59–117.

    Google Scholar 

  • Gupton, Greg, Christopher Finger, and Mickey Bhatia. 1997. CreditMetrics—Technical Document. New York: J.P.Morgan & Co. Inc.

    Google Scholar 

  • Koyluoglu, H., Andrew Ugur, and Hickman. 1998. “Reconcilable Differences.” Risk (Risk), October: 56–62.

    Google Scholar 

  • Jorion, Philippe. 2006. Value at Risk: The New Benchmark for Managing Financial Risk (3rd ed.). McGraw-Hill.

    Google Scholar 

  • Kealhofer, Stephen. 1998. Portfolio Management of Default Risk. San Francisco: KMV Corporation.

    Google Scholar 

  • Liermann, Volker, and Nikolas Viets. 2019. “Predictive Risk Management.” In The Impact of Digital Transformation and Fintech on the Finance Professional, edited by Volker Liermann and Claus Stegmann. New York: Palgrave Macmillan.

    Google Scholar 

  • Liermann, Volker, Iweel Otgontogoo, and Viets Nikolas. 2018. “Immobilienrisiken präventiv analysieren.” RISIKO MANAGER 01|2018, January: 18–24.

    Google Scholar 

  • McNeil, Alexander, Rüdiger Frey, and Paul Embrechts. 2005. Quantitative Risk Management: Concepts Techniques and Tools. Princeton: Princeton University Press.

    Google Scholar 

  • Nonnenmann, Peter, and Xenia Bogomolec. 2021. “Quantum Technologies.” In The Digital Journey of Banking and Insurance, Volume II—Digitalization and Machine Learning, edited by Volker Liermann and Claus Stegmann. New York: Palgrave Macmillan.

    Google Scholar 

  • R Library: CreditMetrics. 02 2015. https://cran.r-project.org/web/packages/CreditMetrics/CreditMetrics.pdf.

  • sparklyr: R interface for Apache Spark. 2018. https://spark.rstudio.com/.

  • Wilde, Tom. 1997. CreditRisk+ A Credit Risk Management Framework. Zurich: CSFB.

    Google Scholar 

  • Wilson, Thomas C. 1997. “Portfolio Credit Risk (I).” Risk 9: 111–117.

    Google Scholar 

  • Wilson, Thomas C. 1997. “Portfolio Credit Risk (II).” Risk 10: 56–62.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Volker Liermann .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this chapter

Verify currency and authenticity via CrossMark

Cite this chapter

Liermann, V., Li, S., Waizner, J. (2021). Distributed Calculation Credit Portfolio Models. In: Liermann, V., Stegmann, C. (eds) The Digital Journey of Banking and Insurance, Volume II. Palgrave Macmillan, Cham. https://doi.org/10.1007/978-3-030-78829-2_7

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-78829-2_7

  • Published:

  • Publisher Name: Palgrave Macmillan, Cham

  • Print ISBN: 978-3-030-78828-5

  • Online ISBN: 978-3-030-78829-2

  • eBook Packages: Economics and FinanceEconomics and Finance (R0)