Advertisement

Large-Scale Data-Driven Financial Risk Assessment

  • Wolfgang BreymannEmail author
  • Nils Bundi
  • Jonas Heitz
  • Johannes Micheler
  • Kurt StockingerEmail author
Chapter

Abstract

The state of data in finance makes near real-time and consistent assessment of financial risks almost impossible today. The aggregate measures produced by traditional methods are rigid, infrequent, and not available when needed. In this chapter, we make the point that this situation can be remedied by introducing a suitable standard for data and algorithms at the deep technological level combined with the use of Big Data technologies. Specifically, we present the ACTUS approach to standardizing the modeling of financial contracts in view of financial analysis, which provides a methodological concept together with a data standard and computational algorithms. We present a proof of concept of ACTUS-based financial analysis with real data provided by the European Central Bank. Our experimental results with respect to computational performance of this approach in an Apache Spark based Big Data environment show close to linear scalability. The chapter closes with implications for data science.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Notes

Acknowledgments

One of the authors (W.B.) thanks the External Statistics Division of the European Central bank for having received him as visitor during his sabbatical. Without the ensuing collaboration this study could not have been carried out. We further thank Drilon Prenaja and Gianfranco Rizza for running the performance experiments as part of their bachelor thesis. The work is funded by the Swiss Commission for Technology and Innovation under the CTI grant 25349.1.

References

  1. Algorithmic Contract Type Unified Standards. (2017). Retrieved from http://actusfrf.org/
  2. ACTUS Data Dictionary. (2017). Retrieved from http://actusfrf.org/index.php/data-dictionary-descriptions/
  3. Bank for International Settlement. (2013, January). Basel committee on banking supervision, principles for effective risk aggregation and risk reporting.Google Scholar
  4. Borthakur, D. (2008). HDFS architecture guide. Hadoop apache project (p. 53).Google Scholar
  5. Brammertz, W., Akkizidis, I., Breymann, W., Entin, R., & Rustmann, M. (2009). Unified financial analysis – the missing links of finance. Hoboken, NJ: Wiley.Google Scholar
  6. CERN. (2017). Retrieved August 31, 2017, from https://home.cern/about/computing/processing-what-record
  7. CreditMetrics. (2017). Technical document. RiskMetrics Group, Inc. Retrieved from https://www.msci.com/resources/technical_documentation/CMTD1.pdf
  8. European Central Bank. (2017). Euro area yield curve. Retrieved from https://www.ecb.europa.eu/stats/money/yc/html/index.en.html
  9. Glassermann, P. (2013). Monte Carlo methods in financial engineering. New York: Springer.Google Scholar
  10. Gross, F. (2014). Setting the standard in a complex world. Financial World. Retrieved from https://fw.ifslearning.ac.uk/Archive/2014/march/features/setting-the-standard-in-a-complex-worldG14
  11. Jenkinson, N., & Leonova, I. S. (2013). The importance of data quality for effective financial stability policies–legal entity identifier: A first step towards necessary financial data reforms. Financial Stability Review, 17, 101–110.Google Scholar
  12. Kambatla, K., Kollias, G., Kumar, V., & Grama, A. (2014). Trends in big data analytics. Journal of Parallel and Distributed Computing, 74(7), 2561–2573.CrossRefGoogle Scholar
  13. Kent, W. (1983). A simple guide to five normal forms in relational database theory. Communications of the ACM, 26(2), 120–125.CrossRefGoogle Scholar
  14. Lightwave. (2017, May 16). RETN to use capacity on AEConnect submarine cable to cross Atlantica. Retrieved August 31, 2017, from http://www.lightwaveonline.com/articles/2017/05/retn-to-use-capacity-on-aeconnect-submarine-cable-to-cross-atlantic.html
  15. Linnemann, V., Küspert, K., Dadam, P., Pistor, P., Erbe, R., Kemper, A., et al. (1988, August). Design and implementation of an extensible database management system supporting user defined data types and functions. In VLDB (pp. 294–305).Google Scholar
  16. Prenaj, D., & Rizza, G., (2016). Performance evaluation of financial algorithms with big data technologies. Bachelor thesis, Zurich University of Applied Sciences.Google Scholar
  17. rActus. (2017). rActus - an R-Interface to the ACTUS contract types. Zurich University of Applied Sciences.Google Scholar
  18. Ramaswamy, S., Sapatnekar, S., & Banerjee, P. (1997). A framework for exploiting task and data parallelism on distributed memory multicomputers. IEEE Transactions on Parallel and Distributed Systems, 8(11), 1098–1116.CrossRefGoogle Scholar
  19. Shadow Banking. (2017). Committee on economic and monetary affairs. Retrieved from http://www.europarl.europa.eu/sides/getDoc.do?type=REPORT&reference=A7-2012-0354&language=EN
  20. Subhlok, J., Stichnoth, J. M., O’hallaron, D. R., & Gross, T. (1993). Exploiting task and data parallelism on a multicomputer. ACM SIGPLAN Notices, 28(7), 13–22.CrossRefGoogle Scholar
  21. Wilkinson, B., & Allen, C. (2005). Parallel programming: Techniques and applications using networked workstations and parallel computers. Upper Saddle River, NJ: Pearson/Prentice Hall.Google Scholar
  22. Vasquez, T. (2011). Weather analysis and forecasting handbook. Garland, TX: Weather Graphics Technologies.Google Scholar
  23. UBS AG. (2008, April). Shareholder report on write-downs. Zurich. Retrieved from http://maths-fi.com/ubs-shareholder-report.pdf
  24. Zaharia, M., Xin, R. S., Wendell, P., Das, T., Armbrust, M., Dave, A., et al. (2016). Apache spark: A unified engine for big data processing. Communications of the ACM, 59(11), 56–65.CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.ZHAW Zurich University of Applied SciencesWinterthurSwitzerland
  2. 2.European Central BankFrankfurtGermany

Personalised recommendations