A year ago, it was hardly unthinkable that a math wizard like David X. Li might someday earn a Nobel Prize. After all, financial economistsâeven Wall Street quantsâhave received the Nobel in economics before, and Li's work on measuring risk has had more impact, more quickly, than previous Nobel Prize-winning contributions to the field. Today, though, as dazed bankers, politicians, regulators, and investors survey the wreckage of the biggest financial meltdown since the Great Depression, Li is probably thankful he still has a job in finance at all. Not that his achievement should be dismissed. He took a notoriously tough nutâdetermining correlation, or how seemingly disparate events are relatedâand cracked it wide open with a simple and elegant mathematical formula, one that would become ubiquitous in finance worldwide. For five years, Li's formula, known as a Gaussian copula function, looked like an unambiguously positive breakthrough, a piece of financial technology that allowed hugely complex risks to be modeled with more ease and accuracy than ever before. With his brilliant spark of mathematical legerdemain, Li made it possible for traders to sell vast quantities of new securities, expanding financial markets to unimaginable levels. His method was adopted by everybody from bond investors and Wall Street banks to ratings agencies and regulators. And it became so deeply entrenchedâand was making people so much moneyâthat warnings about its limitations were largely ignored. Then the model fell apart. Cracks started appearing early on, when financial markets began behaving in ways that users of Li's formula hadn't expected. The cracks became full-fledged canyons in 2008âwhen ruptures in the financial system's foundation swallowed up trillions of dollars and put the survival of the global banking system in serious peril. ... http://www.wired.com/techbiz/it/magazine/17-03/wp_quant?currentPage=all Have fun reading it !
Thank you.... I have been looking for this.... .................................................................................. So since this is at the true core of the blame game.... The question is just who gets to be put on ice ? .................................................................................. The real problem in this case is one of "fitting"....which is a big no no in qualified statistics.... It is clear that this model was adopted before any real world experience working with it .... It was reliant on "back tests" which is basically suicide in financial dynamics.....in that the oncoming set of data is not going to be like the previous sets of data.... So now you have a hungary Wall Street which lost its big commissions in stocks and highly rated debt....which wants to create the next big profit center for itself.... And with the help of its friends....it did.... ........................................................................... So when the moment of truth comes about....the core of the issue is reliance on an unproven concept....guarded by the "nonthreatening world of academical wonder drift".... .......................................................................... But the bottom line with regards to bank behavior is this.... Simple example.... One goes to his local bank and asks what the bank is going to do with the deposit ....The bank replies ...well first we are going to lever 30:1 and buy CCC mortgage debt ....which has never been done before....We feel confident that your money will be secure....even though a 5% downward valuation ....will in effect lose your entire deposit....But do not worry....the government guarantees your deposit.... After the individual hears and understands what the bank is actually doing....the individual immediately requests his/her funds....and seeks another bank.... Only if all depositors knew the real score.
This is stupid. Why blame or scapegoating a single individual for the Credit Model Boom and Bust? So many people helped create the Credit Model bubble, beginning with Robert Merton (the Merton model), Darrell Duffie, Janet Tavakoli, and so on and on and on. Not to mention the legions of greedy bullshitters working at the banks and the rating agencies. Are they implying that the financial system will be saved if they ban the copula functions to model correlations? Stoooooopid. The article is somewhat xenophobic, its point is that it's the chinks who got us in this mess. Riiiight.
Funny been reading a paper by Avellaneda where he mentions in passing don't use copulas and specially not Gaussian ones. Weighted Monte Carlo: A new technique for calibrating asset pricing models Avellaneda M et al
Of course the real issue being just what were the actual steps that took place....names and faces....that accepted this method in order to apply a AAA rating to what should have been CCC or less.... No entity would have bought CCC paper....nada.... Supposedly this was a confirmed method.... Confirmed by some names and faces..... Who were they ? ......................................................................... The point being is that there are a lot of tools on the shelf to pick from....and as the previous commentor suggested ....the blame should not be on the person who creates a mathmatical model.... The blame goes to those who gave the ok to use this particular model and then placed this before the public....far away from the academic world....to where the models have to actually work.... Ok...so where are the names and faces....who depended on academic theory to actually work in the real world ? Of course the model takes future interest rate ranges into account....since the model is interest rate dependent....
No, whatever model they used to price and sell the credit derivatives, the real problem was that too many mortgages were written at too low an interest rate to the wrong individuals. Derivatives only compounded the problem by making mortgages even cheaper and more readily available. This is not a model problem. In fact I think that credit derivatives are a good idea and a valid innovation, but they will amplify the effects of misguided monetary and real estate government policies. That the models were used to "hide" risk and give "bullshit" ratings, that was another problem, but that's the people who inadequately used the mathematics, for example, did not make the assumptions explicit etc.
The people in charge used the models as marketing props. They went by their gut feel and in an elongated super cycle the gut always gets it wrong for the majority.
The people in charge knew exactly what was going on, don't kid yourself. All that mattered is that they got paid. Noone in charge actually believes in Li's model. He is just another easily manipulated geek with no tact. Just reading the article makes me laugh about how naive Li is.