|
PureBytes Links
Trading Reference Links
|
Aside from the curve-fitting aspect of walk forward testing,
and the seductive confidence it provides, I'd like to raise
still another objection: it is conceptually flawed.
Aside from data-fitting, another cause of system degradation
in real-time, as well as discretionary traders finding the
markets more difficult, is due to the fact that markets
evolve. Today's markets, are not your father's markets.
Anybody with a chart, no less a computer, can make money
paper-trading markets of 5 - 10 years ago.
Thus, what I often do in my system development, is to
create systems that work on the most RECENT 1 - 2 years. I
don't do data mining, but rather start with sound conceptual
trading principles, that I observe working now.
After translating the principles into specific rules, I
quantify them, & test them on recent data. I mostly look at
the way the system acts, rather than mere statistical
results. If I'm satisfied with the system behavior, as well
as the various stats, then I can test it on prior years'
data. If it even breaks-even over the prior years, I may
trade it.
Contrast this to walk forward, where you test on old data,
then "blindly" test on the most recent periods. Yes, some
concepts may work equally over extended periods, but if the
goal is at all to be more in sync with current conditions,
you will probably not achieve that, as all your development
is on prior, out of sync, periods.
Thus, I'm proposing that walk BACKWARD testing is far more
sound conceptually, and is likely to lead to better results
than the walk forward methodology.
----- Original Message -----
From: "--" <hadrada@xxxxxxxxxxx>
To: "Mark Brown" <markbrown@xxxxxxxxxxxxx>;
<omega-list@xxxxxxxxxx>
Sent: Saturday, May 05, 2001 9:55 AM
Subject: Re: Re[2]: Trading Systems
> : walking forward with mush boy oh boy does anyone
remember
> : alon shadammie the walk forward king?
>
>
> I thought the walk forward king was Joe Krutsinger. I
remember that at a
> 'demonstration' of his $7,500 system ('Time Machine') at
an NYC Omega Users
> Group meeting, he mention that it must be re-optimized
every week (on EOD
> data) and he calls this 'walk forward' testing. How about
calling it for
> what it truly is, 'curve fitting'? He also mentioned that
he doesn't make
> money from trading but from providing 'advice', 'systems'
and 'services' to
> those who do.
>
|