Home » post » Bad data and bad computer models led to financial crisis

Our mission

Free Government Information (FGI) is a place for initiating dialogue and building consensus among the various players (libraries, government agencies, non-profit organizations, researchers, journalists, etc.) who have a stake in the preservation of and perpetual free access to government information. FGI promotes free government information through collaboration, education, advocacy and research.

Bad data and bad computer models led to financial crisis

As a data services librarian and an one-time economics bibliographer, I have been following with great interest the way many different people are identifying the source of our current financial crisis as a combination of bad data and bad financial models. Although this is not directly related to government information, I know some of you answer questions about economics, business, and related fields and may find these links helpful.

I think part of my fascination with this is how we keep hearing financial people justifying their “mistakes” by saying that this is a rare event. “Who could have foreseen this?” they say. But these articles say it is precisely the fact that investors ignored the possibility of rare events that caused the problem.

These all have some common ground, but my favorite short-hand is the explanation by Nicholas Taleb. (The Fourth Quadrant: A Map Of The Limits Of Statistics, by Nassim Nicholas Taleb, Edge, Sept. 15, 2008.) He is the author of The Black Swan which is about “highly improbable and unpredictable events that have massive impact.” He compares the financial crisis to the situation of a turkey before Thanksgiving.

A Turkey is fed for a 1000 days — every day confirms to its statistical department that the human race cares about its welfare “with increased statistical significance”. On the 1001st day, the turkey has a surprise.

He compares that with the fate of close to 1000 financial institutions that were betting against a “rare event””

Others:

  • How Wall Street Lied to Its Computers. by Saul Hansell. New York Times Bits Blog, September 18, 2008. “The people who ran the financial firms chose to program their risk-management systems with overly optimistic assumptions and to feed them oversimplified data.”
  • Recipe for Disaster: The Formula That Killed Wall Street, by Felix Salmon.Wired, February 23, 2009. “Li’s Gaussian copula formula will go down in history as instrumental in causing the unfathomable losses that brought the world financial system to its knees.”
  • Wired and the Math Formula of Doom, by Ryan Chittum, Columbia Journalism Review, February 26, 2009. “Disclosure’s great. Journalists love it. We need it to inform the public and the public needs it to make good decisions. But it’s naive to think it will enable Mr. Market to work his magic and all will be well. Tough rules with teeth are going to have to accompany fuller disclosure.”
  • In Letter, Warren Buffett Concedes a Tough Year, By David Segal New York Times, March 1, 2009. “He went on: “These parties looked at loss experience over periods when home prices rose only moderately and speculation in houses was negligible. They then made this experience a yardstick for evaluating future losses.”
  • The Terminator Comes to Wall Street, By Joseph Fuller, The American Scholar, March 1, 2009. “The first problem is that those who created the models don’t understand the markets…. The second problem is that managers don’t understand the modelers.”

Finally, and perhaps related to all the above, Sherry Turkle professor of the social studies of science and technology at the Massachusetts Institute of Technology, is writing a book about computer simulations and finds problems with using them.

In my book, I tell the story of a girl who was a power player of the game Sim City. She talked to me about her “David Letterman Top Ten Rules of Sim City,” and rule number 6 was “raising taxes leads to riots” because when she did that, that happened in the game. She didn’t understand that if I had programmed that computer, raising taxes would’ve led to more social services and greater social harmony. She was drawing a set of conclusions about how the world worked based on the simulation. The trouble with that was not that she was using the simulation, but that the simulation wasn’t transparent to her.

    – Simulations May Be Causing Real Trouble, interview with Sherry Turkle. Chronicle of Higher Education, Wired Campus Blog, March 13, 2009.

CC BY-NC-SA 4.0 This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.


Leave a comment

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Archives