Building a “Robust” Forex Trading System

I would construct a theory and work on its lines until I found it was untenable. Then it would be discarded at once and another theory evolved. This was the only possible way for me to work out the problem. … I speak without exaggeration when I say that I have constructed 3,000 different theories in connection with the electric light, each one of them reasonable and apparently likely to be true. Yet only in two cases did my experiments prove the truth of my theory. – Thomas Edison

Building a “Robust” Forex Trading System

When building a trading system, you want it to be Robust, meaning that it is able to adapt to changing market conditions.  If your system responds well to changes in the market, you are effectively reducing risk.

A Robust System has the following properties:

  1. Simple: If your system is too complex, you’ve over optimized.  You should use no more than 3-5 parameters.  Try to use “simple strategies using simple concepts derived from a fundamental view of how the markets develop” (1)
  2. Profitable across markets
  3. Profitable over a range of parameters:  In the case of a Moving Average cross, a 20 MA shouldn’t be the only profitable choice.  It should also work between a span of values such as a 17 and 22 MA.   This way if the market changes your system will still work.
  4. Consistent Risk Ratios: Win/Loss ratio, Average Profit & Loss, Max Drawdown

Is your system robust?

  1. If you marginally change your Take Profit (Increase or decrease by a pip or 5 pips), what affect does this have on your profit?  Are you still profitable?
  2. Try moving your parameters around by one or two points, is it still profitable?

Identifying Trade Filters:  To increase the robustness of your system, we can apply filters in order to increase Consistency.  Some filters may include the following

  1. avoid trades in times of Low Volatility (Volatility Adaptive Criteria)
  2. avoid trading in a ranging market

 

References and Further Reading:

  1. http://mechanicalforex.com/2010/10/robustness-ideal-system-characteristics-to-withstand-change.html
  2. http://turtletrader.com/curve-fit/
  3. http://www.forex-learning-site.com/blog/2008/how-to-build-and-backtest-a-robust-forex-trading-system/ 
This entry was posted in System Design. Bookmark the permalink.

Leave a comment