Daily Speculations The Web Site of Victor Niederhoffer and Laurel Kenner
Dedicated to the scientific method, free markets, ballyhoo deflation, value creation and laughter.
A forum for us to use our meager abilities to make the world of specinvestments a better place.
Write to us at: (address is not clickable) |

Kim Zussman

11/01/2005

The Million Mind March, by Kim Zussman

Say one won $100 million in the lotto (appropriately known as a tax on people who are bad at math), and sought to exponentiate so as to cure malaria.

So ran ad in the math departments of the top SAT universities, which promised a position at a new fund running statistical patterns. After screening a large number of candidates, hired 100 traders. They were put in a large office, with 100 cubicles containing identical computers loaded with several statistical packages and complete data series for all widely traded markets.

All traders were required to read certain books on markets, and after a week's training on the system there was a big meeting. Each trader was charged with coming up with profitable patterns and checking them for statistical significance. Every day, they would be allowed to send their studies in, but only if they had significance better than p=0.05. For each study accepted, they would be paid $100 in the near future (note that no dental hygienists applied for the job).

After a short while, and hundreds of significant results and thousands in principal reduction, the intrepid entrepreneur has a revelation. With p of 5%, there is 1/20 chance that trader's studies will show significance even if the pattern has no predictive value. And if the 8000 hedge funds average 10 such traders each, and for each of those are several prop traders and privates, there are a million minds poring over the same data for pockets of profits.

The real information sought is not historically repeating patterns, but insight into the collective reactivity of the multi-cellular mind of the market. Perhaps the guy should shell out for a functional PET scanner, and study labeled-glucose uptake in the limbic system of traders faced with statistical patterns in trading real money.