|
PureBytes Links
Trading Reference Links
|
Two things I've found useful for getting optimizations done faster are:
1) optimize independent variables separately and recursively. For example,
perhaps your entry parameters don't affect your exits and your exit
parameters don't affect your entries. (or size parameters don't affect
entries and exits, or subsystem A's parameters don't affect subsystem B,
etc.) Set the "other" parameters to something reasonable. Optimize the
first set of parameters. Using these optimal parameters go on to optimize
the "other" parameters. Now come back are re-optimize the first set. Keep
re-optimizing until all parameter sets are stable.
2) increase the stepsize in your optimizations to roughly scan the parameter
space first to find the peaks. Then do your detailed optimization in these
smaller, promising areas.
Even though these methods will cause you to do more optimizations to get to
a final answer, many small optimizations usually go faster than one big one.
Please let me know if you find something else you like.
Regards,
Aaron Schindler
Schindler Trading
----- Original Message -----
From: "Ron Hughes" <ronaldehughes@xxxxxxxxxxx>
To: <omega-list@xxxxxxxxxx>
Sent: Thursday, June 20, 2002 8:21 PM
Subject: Backtesting
> Hello Group,
>
> I have a question I was hoping some of you might be
> willing to answer. I am doing some back-testing in order to optimize the
> inputs on a system that I've developed. The time required to complete this
> process seems rather excessive, five hundred hours. Is there any way to
> speed up the back-testing process, or is the time required simply a
function
> of the number of variables in the equation and the limitations of the
user's
> hardware.? Your comments would be greatly appreciated.
>
> Happy Trading,
>
> Ron.
>
|