This neural network developer details steps in developing a trading system using advanced technology."STOCKS & COMMODITIES readers have one thing in common: We have all taken on the challenge of attempting to forecast and trade the financial markets. For me, I first considered this challenge as the result of a chance remark. Since I had also become curious about trading at the time, I decided to take on the challenge of modeling the markets. That was more than a decade ago."
I realized that in order to succeed, I had to do four things: First, spend time on the problem; second, learn more about trading and the markets; third, develop specialized tools; and fourth and most important, develop a computerized system to eliminate subjectivity.
"In addition to the advantages produced by formalizing trading ideas, a fully mechanized system would also allow me to factor in the gotchas -- things such as commissions, slippage, impossible fills and markets that move before I can. One problem I had was failing to consider the high transaction costs involved in trading OEX options. Through complete mechanization, I could ensure that my systems would include all such factors. In this way, I could eliminate potential surprises as well as obtain a very realistic assessment of how any system performs."
"To be a winning trader, it is necessary to search for obscure inefficiencies or those that require specialized technology, or for rare events that can be traded together in a metasystem on time frames that are not popularly traded, so that the stiff competition can be sidestepped. One needs to look for that proverbial needle."
