The new Manhattan Project

As we watch the stock market sink to 1997 levels, this article in Wired Magazine should send chills down your spine. It says a formula created by a Chinese-born mathematician, David X. Li, might have set in motion the collapse of Wall Street and our economy. This model was invented to reduce financial uncertainty, and for a while it worked. Until it didn't.

The formula is known as the Gaussian Copula Function. In this complex-looking-but-ultimately-too-simple equation, financial institutions saw major dollar signs. They started using it to do something they couldn't do before: price multiple securities and assess their risk. Yes, I'm talking about bundled-up mortgage-backed securities.

From the article:

His method was adopted by everybody from bond investors and Wall Street banks to ratings agencies and regulators. And it became so deeply entrenched--and was making people so much money--that warnings about its limitations were largely ignored.

It's limitations became abundantly clear last year, "when financial markets began behaving in ways that users of Li's formula hadn't expected."

Li won't talk about it now. He works in China in the risk management department of China International Capital Corporation.

But he has said this about his model: "The most dangerous part is when people believe everything coming out of it."

It kind of makes you think about Albert Einstein and the atomic bomb. Einstein's Theory of Relativity was the starting point. Li didn't send a letter urging his bomb to be built, but he told Wall Streeters they didn't have to look beyond his simple formula. That's all they needed to make a fortune.

And now Einstein's words ring true:

The difference between stupidity and genius is that genius has its limits.

Log in to post6 Comments

Actually, Li did warn Wall Streeters to look beyond his simple formula back in 2005. It is even documented in the Wall Street Journal.

This is from Felix Salmon's article:
"...No one knew all of this better than David X. Li: 'Very few people understand the essence of the model, he told The Wall Street Journal way back in fall 2005. 'Li can't be blamed,' says Gilkes of CreditSights. After all, he just invented the model. Instead, we should blame the bankers who misinterpreted it. And even then, the real danger was created not because any given trader adopted it but because every trader did. In financial markets, everybody doing the same thing is the classic recipe for a bubble and inevitable bust...."

Why is there no discussion about the legislation that allowed this simple distribution to be used to combine A rated investments with risky ones and sell the package as A rated?
There was no easily available data on the history of house prices in 2000. The gamma value in Li's formula had to be based on insufficient data.
I feel the real problem is that we allowed Phil Graham to talk us into relaxing market regulation that had protected us since the great depression.

I doubt Li (or any statistician) would ever say "don't look beyond this simple formula"; all probabilistic estimates rely upon assumptions, and in cases where those assumptions are violated, resulting estimates are garbage. Instead, I suspect that Wall Streeters deluded themselves into thinking his simple formula was universally applicable --- even when its underlying assumptions were violated. As an investor, I'm told "caveat emptor"; similarly, Wall Streeters should be wary of buying into analysis techniques that quants cook up.

This sound just like the Long Term Capital Management / Fixed Income Arbitrage: "picking up nickels in front of a steam roller" mistake. The real travesty are bailouts that allow this kind "accident", with increasing amplitude, every ten years!

With Generous Support From...