Using System Feedback to Improve Trading System Performance
A mechanical trading system is really a predictive model of a given market. Many predictive models suffer from the effect of noise or an inadequate understanding of the problem being modeled. In most fields outside of trading, the errors of the last few forecasts are analyzed in order to improve future forecasts. This concept is called feedback. Most predictive models output numerical values. A simple trading system has four discrete values: (1) long, (2) exit long, (3) short, and (4) cover.
HOW FEEDBACK CAN HELP MECHANICAL TRADING SYSTEMS
In a mechanical trading system, feedback is valuable in efforts to identify which signals from the system have the highest probability of being profitable. Feedback also helps in selecting which system to trade when multiple systems are trading in the same market. Later in this book, we will discuss how to implement this application using advanced technologies such as machine learning.
HOW TO MEASURE SYSTEM PERFORMANCE FOR USE AS FEEDBACK
We measure the performance of a system based on its trade history. We can look at the trading results from two different perspectives: (1) on the basis of only closed-out positions, or (2) on a bar-by-bar basis, by recording the opening equity of each position. In this book, we will study only the equity of closed-out positions.
We also can consider ...