Thread: My first EA seems to give good results - how much to trust them?
View Single Post
  #9 (permalink)  
Old 08-26-2006, 02:47 AM
Devil2000 Devil2000 is offline
Senior Member
  
Join Date: Dec 2005
Location: In front of my trading desk
Posts: 348
Devil2000 is on a distinguished road
Quote:
Originally Posted by TraderSeven
No special reason. Optimize on 2001 and test on 2003 is fine too.
The danger of optimizing is that the settings only work on the data you used.
If you optimize on year X and test on year Y you have proof that the settings 'always' work and not just on the backted data.

(Over) optimizing, also called curve fitting, can give you +100% on the data you optimized on and -100% on all other data.
Signs of over optimization are often that there are a lot of loosers and the profit comes from one big killer profit.
I think optimizing for 2005 and 2006 maybe better, at least you test in on latest market behaviour, it will give you a bit confident but nothing is compared to live test. Good luck then.
Reply With Quote