How to adapt an optimized strategy over time

Viewing 2 posts - 1 through 2 (of 2 total)

Author

Posts
05/19/2017 at 10:05 AM #36077 quote

Francesco78
Participant

Master

Suppose you are running a 1hr strategy.

3yr Backtest.

WF 70/30 test passed

5 variables optimized.

first approach: reoptimizing over the last 6 monhts every 3 month.

second approach: reoptimizing over the max period available every month.

Which one would you choose ideally?

Many thanks.

Francesco

05/19/2017 at 2:29 PM #36105 quote

Maz
Participant

Veteran

It really depends on the system and what the variables actually control. Anything that includes moving averages is highly subject to curve fitting and so you should be aware of what the typical effective cycles are.

We optimize H1 systems at least every week for the last 3 -6 months. (Systems that run in seconds we optimize every day!) We also check the previous week’s 3-month optimization backtest against the previous week’s actual performance. If they are not too different, we can keep things the same. If they become more and more different over a few weeks then we need to update the live system.

Francesco78 thanked this post
Author

Posts

Viewing 2 posts - 1 through 2 (of 2 total)

You must be logged in to reply to this topic.

Login your account

How to adapt an optimized strategy over time

ProOrder: Automated Strategies & Backtesting

New Reply

Author

Francesco78 @francesco78 Participant

Summary

This topic contains 1 reply,
has 2 voices, and was last updated by Maz
8 years, 9 months ago.

Topic Details

Forum:	ProOrder: Automated Strategies & Backtesting
Language:	English
Started:	05/19/2017
Status:	Active
Attachments:	No files

Loading...