“Artificial Intelligence” To Be Implemented In HFT

The increasingly fast electronic trading systems have become too fast for humans to handle. We are now seeing a wave of  investment firms turning to the science of artificial intelligence to make investment decisions. Unlike most Wall Street actors, the trading robots are capable of learning from their mistakes.

“No human could do this. Your head would blow off.”

Michael Kearns

With artificial intelligence, programmers don’t just set up computers to make decisions in response to certain inputs. They attempt to enable the systems to learn from decisions, and adapt. Investors using the approach are implementing “machine learning”  – a branch of artificial intelligence in which a computers analyzes huge chunks of data to make predictions about the future.

The following post is based on an article by Scott Patterson, journalist with The Wall Street Journal, one of the few mainstream reporters who really understand the HFT business.

Scott Patterson

The original article was published in July this year, but have until recently only been available to WSJ’s subscribers.

According to Patterson, there’s a new wave of firms using machine learning to trade.

With artificial intelligence, programmers don’t just set up computers to make decisions in response to certain inputs. They attempt to enable the systems to learn from decisions, and adapt.

Most investors trying the approach are using “machine learning,” a branch of artificial intelligence in which a computer program analyzes huge chunks of data and makes predictions about the future.

It is used by tech companies such as Google to match Web searches with results and NetFlix to predict which movies users are likely to rent.

Young Geeks In Action

Rebellion Research

One of the new upstart in the AI race on Wall Street is Rebellion Research, a tiny New York hedge fund with about $7 million in capital that has been using a machine-learning program it developed to invest in stocks.

Run by a small team of twenty-something math and computer whizzes, Rebellion has a solid track record, topping the Standard & Poor’s 500 stock index by an average of 10% a year, after fees, since its 2007 launch through June, according to people familiar with the fund.

Like many hedge funds, its goal is to beat the broader market year after year.

“It’s pretty clear that human beings aren’t improving,” says Spencer Greenberg, 27 years old and the brains behind Rebellion’s AI system. Adding:  “But computers and algorithms are only getting faster and more robust.”

Some sophisticated hedge funds such as New York based Renaissance Technologies LLC are said to already have deployed AI to their investing programs.

For years, these firms were the exceptions. But not anymore.

The Rise of The Machines

Rebellion is part of a new wave of firms using machine learning to trade. Cerebellum Capital, a San Francisco hedge fund with $10 million in assets, started using machine learning to invest in 2009, according to Patterson and The Wall Street Journal.

A number of high-frequency trading firms, such as RGM Advisors LLC in Austin, Texas, and Getco LLC in Chicago, are using machine learning to help their computer systems trade in and out of stocks efficiently, says people familiar with the firms.

The programs are effective, advocates say, because they can crunch huge amounts of data in short periods, “learn” what works, and adjust their strategies on the fly.

In contrast, the typical quantitative approach may employ a single strategy or even a combination of strategies at once, but may not move between them or modify them based on what the program determines works best.

Will Blow Your Head Off

“No human could do this,” says computer scientist, Professor Michael Kearns, at the University of Pennsylvania who has used AI to invest at firms such as Lehman Brothers Holdings Inc. “Your head would blow off.”

Rebellion has struggled to raise money, in part because investors since the credit crisis are dubious of opaque math-based strategies.

The firm has attracted at least one long-time “quant” skeptic: famed value investor Jean-Marie Eveillard, who recently invested several hundred thousand dollars of his own money into Rebellion.

“My cup of tea is not quantitative investing,” he says. “But I think they are serious investors, and I’m impressed by the fact that they don’t have a high turnover…and don’t use leverage.”

Read the full post at The Swapper:

Related by the Econotwist:

The Ultimate Trading Weapon

Survey: Market Surprised By Negative Derivative Perception

Testimony Of A High Frequency Trader

The Rise Of The New Market Makers

Flight to Mystery

May 6. 2010: “The Black Thursday”

Wall Street Collapse: Did Somebody See It Coming?




Filed under International Econnomic Politics, National Economic Politics

3 responses to ““Artificial Intelligence” To Be Implemented In HFT

  1. Pingback: Understanding High Frequency Trading « The Swapper

  2. Brilliant blog, I hadn’t noticed econotwist.wordpress.com previously in my searches!
    Continue the superb work!

  3. Sharing good health to your hands