O'Reilly logo

Building Algorithmic Trading Systems: A Trader's Journey From Data Mining to Monte Carlo Simulation to Live Trading, + Website by Kevin J. Davey

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

CHAPTER 19 Monte Carlo Testing and Incubation

With the walk-forward testing complete, based on the results I am confident I have a viable strategy. The equity curve for walk-forward testing looks nice, but at the same time I realize that there is no possible way the future equity curve will look exactly like the past equity curve. My hope, and the hope of all developers at this stage, is that the components of the equity curve (i.e., individual trades) are roughly the same as the walk-forward history. The easiest way to imagine this is to think about the average trade profit and its standard deviation (scatter). If either of these values significantly changes, the system might fail in the future. If, for example, the average trade turns negative, future performance will obviously be negative. Similarly, if the standard deviation increases, the drawdowns will likely be much more severe, the system will be harder to trade with position sizing, and the resulting equity curve will probably give you more ulcers.

Assuming, then, that the walk-forward trade performance will continue in the future, it becomes useful to see how the future performance might vary over time. For this analysis, I simulate one year’s worth of trades with Monte Carlo analysis.

images Euro Day Strategy

As previously discussed in Chapter 7, the only information required to do a simple Monte Carlo analysis is:

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required