For Renowned Speed Trader, Humans Not Allowed Anywhere Near High-Frequency Execution System

Posted on July 27, 2011. Filed under: Flash Crash, Strategies, Technology | Tags: , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |

It took a while for Adam Afshar, one of the leading high-frequency traders featured in Edgar Perez’s The Speed Traders: An Insider’s Look at the New High-Frequency Trading Phenomenon That is Transforming the Investing World, to believe that the markets were more or less efficient under normal circumstances and to realize that the analysts at most firms provided no value and sometimes a negative value. He says, “My first attempt at using the computer was to build a system to help traders have better information faster to enable them or their portfolio managers to make better decisions, a sort of hybrid system where the computers are helping the humans. But, in less than a year, I realized that discretionary human participation in selection, portfolio management , or trading was so deleterious that no amount of computer power or intellectual algorithms  could mitigate it.”

Adam Afshar

Adam Afshar, Renowned Speed Trader- Hyde Park Global Investments

He adds: “It’s very important to stress this point because if the system allows human discretion at any level (idea generation, portfolio management, or trading) and your machine does not have the human discretionary elements modeled correctly in its learning algorithm (which we claim is not possible at this time), what you are left with is simply a quantitative trader  that uses certain calculations to assist his or her trading. It becomes difficult or even impossible to assess whether the success or failure was due to the calculations, formula, or algorithms . Although we can argue on the pros and cons of humans as traders, we have to agree that this method is not and cannot be scientific. It is not scientific because it is not possible to backtest a model that allows any discretionary human intervention. For example, if you have computers  that are generating trades, but the execution is done by humans, then we would argue that you cannot determine whether the success or failure of the system was due to its robust artificial intelligence  or to a very good trader, and there is no way of testing and duplicating the results. Therefore, we would argue that any backtesting becomes essentially void.”

Hyde Park Global Investments, Afshar’s firm, is an investment and trading firm that has developed an artificial intelligence system built primarily on genetic algorithms and other evolutionary models to identify mispricings, arbitrage, and patterns for many electronic financial markets  and the robotic platform  to monetize the opportunities. The firm, which trades its own capital so far, potentially will accept investments from outside sources.

Read Full Post | Make a Comment ( None so far )

Liked it here?
Why not try sites on the blogroll...