The Man Who Solved the Market: How Jim Simons Launched the Quant Revolution

by Gregory Zuckerman

It didn’t take Baum long to develop an algorithm directing Monemetrics to buy currencies if they moved a certain level below their recent trend line and sell if they veered too far above it. It was a simple piece of

Strategies

work, but Baum seemed on the right path, instilling confidence in Simons.

Monemetrics would invest a bit of money for Simons, testing strategies in a variety of markets. If the tactics looked profitable, Simons would place the same trades in Limroy, which was much bigger and would invest for outsiders as well as for Simons. Baum would share in the 25 percent cut the firm claimed from all its trading profits.

Hullender created to track prices and test various trading strategies based on both mathematical insights and the intuitions of Simons, Baum, and others. Many of the tactics they tried focused on various momentum strategies, but they also looked for potential correlations between commodities. If a currency went down three days in a row, what were the odds of it going down a fourth day? Do gold prices lead silver prices? Might wheat prices predict gold and other commodity prices? Simons even explored whether natural phenomena affected prices. Hullender and the team often came up empty, unable to prove reliable correlations, but Simons pushed them to keep searching.

His early research wasn’t especially original. Ax identified slight upward trends in a number of investments and tested if their average price over the previous ten, fifteen, twenty, or fifty days was predictive of future moves. It was similar to the work of other traders, often called trenders, who examine moving averages and jump on market trends, riding them until they peter out. Ax’s predictive models had potential, but they were quite crude. The trove of data Simons and others had collected proved of little use, mostly because it was riddled with errors and faulty prices. Also, Ax’s trading system wasn’t in any way automated—his trades were made by phone, twice a day, in the morning and at the end of the trading day.

note

It wasn’t immediately obvious why some of the new trading signals worked, but as long as they had p-values, or probability values, under 0.01—meaning they appeared statistically significant, with a low probability of being statistical mirages—they were added to the system.

P value