The Monte Carlo method
1 replies
AndrEAs SQ
10 years ago #111665
AndrEAs
Mark Fric
10 years ago #122846
Hello,
Monte Carlo method is an important tool, it tells you how your strategy behaves when input conditions are slightly changed.
Ideally you want your EA to be robust and don’t break apart when parameters or data change slightly.
This is what differences curve fitted strategies from robust ones – robust strategy should “survive” also Monte Carlo test.
I wouldn’t skip Monte carlo test, maybe you can experiment with its setting and find what type of test (there are few different like skipping orders, randomizing history data, randomizing parameters, etc.)
cause your strategy failure. Then you’ll know what your strategy is sensitive of.
But I usually use the default setting and expect the strategy to pass the test completely.
Mark
Mark
StrategyQuant architect
Viewing 1 replies (of 1 total)