|
PureBytes Links
Trading Reference Links
|
Michael I wonder what results you would get if you
used a 10 year cycle. What I mean is train your net based on 1990-91 data and
run your test on 2000-01. I believe this is one of Gann's cycles as he made
yearly forecasts using the composites of 10 year cycles.
So you could look at 70-71, 80-81, 90-91. The only
problem you might have is the volatility based on price so you may need to look
at the percentage of the move instead of the actual points.
I would be interested in seeing these results if
you have the time, data and inclination
Thanks
Steve
<BLOCKQUOTE
style="PADDING-RIGHT: 0px; PADDING-LEFT: 5px; MARGIN-LEFT: 5px; BORDER-LEFT: #000000 2px solid; MARGIN-RIGHT: 0px">
----- Original Message -----
<DIV
style="BACKGROUND: #e4e4e4; FONT: 10pt arial; font-color: black">From:
<A title=MikeSuesserott@xxxxxxxxxxx
href="mailto:MikeSuesserott@xxxxxxxxxxx";>MikeSuesserott@xxxxxxxxxxx
To: <A title=omega-list@xxxxxxxxxx
href="mailto:omega-list@xxxxxxxxxx";>omega-list@xxxxxxxxxx ; <A
title=realtraders@xxxxxxxxxxxxxxx
href="mailto:realtraders@xxxxxxxxxxxxxxx";>realtraders@xxxxxxxxxxxxxxx
Sent: Thursday, January 31, 2002 4:53
PM
Subject: [RT] Neural Nets
Have been playing around a little with a neat present I had
bought formyself last Christmas - Neuroshell Daytrader (<A
href="http://www.neuroshell.com";>www.neuroshell.com). Here arethe
results of one system that came up in testing. As you will see from
theattached chart, neural nets are by no means perfect, but it looks like
theycan make money for you.This very crude QQQ system is based on
30-min. data starting Jan. 2001. Itdoesn't use stops and is always in the
market. The net was trained on dataup to Oct. 9, 2001, then tested on
out-of-sample data from Oct. 10 throughOct. 24. Following that, it was
retrained using the additional two weeks ofdata up to Oct. 24, and applied
on the out-of-sample data from Oct. 25through Nov. 7. In this manner, a
series of 2-week-long walk-forward testson out-of-sample data was
produced, with the net being retrained every twoweeks the way it would
have been done in real trading, too.In spite of some whipsaw, the
system proves quite profitable with anannualized return of 193.9%
(statistics attached). While I still reservejudgment on the general value
and applicability for my trading, I must saythe results of testing so far
look promising.Best regards,Michael
SuesserottDisclaimer: I have no connections with Ward Systems except
as a customer.To
unsubscribe from this group, send an email
to:realtraders-unsubscribe@xxxxxxxxxxxxxxxYour
use of Yahoo! Groups is subject to the <A
href="http://docs.yahoo.com/info/terms/";>Yahoo! Terms of Service.
Yahoo! Groups Sponsor
To unsubscribe from this group, send an email to:
realtraders-unsubscribe@xxxxxxxxxxxxxxx
Your use of Yahoo! Groups is subject to the Yahoo! Terms of Service.
|