Considered cutting edge on Wall Street these days, algorithmic trading involves predicting prices and volume several seconds forward. Many of the strategies originated within small, proprietary trading houses.

The term "statistical arbitrage" is something of a misnomer. "Arbitrage implies that we are locking in a risk-free profit, but that isn’t what we're doing," says David Shaw, chairman and founder of D.E. Shaw, one of the oldest statistical arb shops, founded in 1988. A more accurate label, in his view: algorithmic trading. Essentially, statistical arbitrage strategies are driven by computer algorithms that are designed to recognize stock price patterns and to identify deviations that can be expected to quickly revert to the norm.

Another secretive firm is Morgan, which hired a Columbia University computer scientist for its Automated Analytical Trading Group. Morgan, which declined requests to discuss its use of minisupercomputers, has placed an ad in technical journals to recruit "algorithmic trading scientists."