Financial Network Analytics @ Bank of Canada


Published on

Presentation at Bank of Canada workshop on "Understanding financial markets and institutions - Theory and Data" on 2 June 2011 in Ottawa, Canada.

Published in: Economy & Finance
  • Be the first to comment

  • Be the first to like this

No Downloads
Total views
On SlideShare
From Embeds
Number of Embeds
Embeds 0
No embeds

No notes for slide

Financial Network Analytics @ Bank of Canada

  1. 1. Presentation at Bank of Canada <br />Workshop on Understanding Financial Institutions and Markets: Theory and Data<br />2 June 2011<br />Financial Network Analytics<br />Kimmo Soramäki<br /><br />
  2. 2. Perspective<br />Understanding financial institutions and markets<br />Theory<br />Data<br />Focus on the tools and processfor research and policy<br />
  3. 3. Katsushika Hokusai. The great wave off Kanagawa ~1830<br />
  4. 4. Eratosthenes' map of the known world, c. 194 BC<br />
  5. 5. Go is a board game that originated in China more than 2,000 years ago. <br />
  6. 6. Data deluge<br />Data tsunami - digital information is doubling every 1.2 years<br />Regulatory response to recent financial crisis was to strengthen macro-prudential supervision with mandates for more regulatory data<br />The challenge will be to understand and analyze the data (public, commercial and regulatory)<br />Data enables “Analytics based policy”, i.e. the application of computer technology, operational research, and statistics to solve problems<br />
  7. 7. Network maps<br />Recent financial crisis brought to light the need to look at links between financial institutions<br />Way to present data. Mapping of the financial system has only begun<br />Reduce uncertainty about interconnections <br />Garrett, Mahadeva and Svirydenska (2011)<br />Soramaki, Bech et al (2006)<br />
  8. 8. Intelligence<br />Financial crisis are different and rare <br />Pattern recognition is hard for computers -> the best Go programs only manage to reach an intermediate amateur level<br />The patterns to be recognized must be frequent enough for computers to learn<br />A solution is to augment human intelligence (in contrast to AI)<br />
  9. 9. Roots of the work<br />Bof-PSS2<br />Bank of Finland, 1997-<br />Payment system simulator used in ~60 central banks<br />Loki<br />Sandia National Laboratories, 2004-<br />Toolkit for network analysis and ABM<br />Sponsored by Norges Bank, collaborative efforts with other central banks<br />
  10. 10. Method and features<br />
  11. 11. Data tools in FNA<br />
  12. 12. Network analysis in FNA<br />
  13. 13. Network visualization in FNA<br />
  14. 14. Demo<br />
  15. 15. Versions<br /><ul><li>Web
  16. 16. Cloud service
  17. 17. REST API (for accessing FNA engine from web applications)
  18. 18. Intranet
  19. 19. Operative use
  20. 20. Integration to databases and user management
  21. 21. Browser based GUI
  22. 22. Desktop
  23. 23. By demand, academic use
  24. 24. Command line version available
  25. 25. Integration with external programs like Matlab, Stata, Excel, etc.</li></li></ul><li>Availability<br />Private beta in July 2011<br />Official release in August 2011<br />Core (graph engine, algorithms, visualizations) is open source (GPL) <br />Desktop version is free for academic use<br />
  26. 26. Vision<br />Develop tool for explorativeanalysisof the financial system<br />Provide a platform for building agent based and simulation models<br />Make advances in research available to policy<br />Integrate data feeds and available databases<br />
  27. 27. Thank you<br />More information<br /><br />Contact us<br /><br />