|
PureBytes Links
Trading Reference Links
|
<SPAN
class=616475318-29092003>thanks for answering steve, and apologies for asking
you to interpret dave's stuff. you were handy (:-)... I'll post anything
interesting if dave is able to reply.
<SPAN
class=616475318-29092003>
<SPAN
class=616475318-29092003>I agree in principle that constant adjustment is the
way to go. I just posted a long msg to the VectorVest group to the effect
that real life effectively *is* a walk-forward optimization. any parameters
you're presented with today result from tests on earlier data, not some eternal
truth, and this process of evolution can't stop.
<SPAN
class=616475318-29092003>
<SPAN
class=616475318-29092003>am I understanding you to be saying that the main way
you optimize is to confine relatively static scans to a watchlist of things that
have been performing well lately with your system? it's interesting, I was
working on a system that appeared to do much better than average over a wide
range of issues, and the best predictor of future success I found was past
success. had to trash it because it turned out the nice returns were due to
accidentally peeking into the future a bit, but the optimization principle made
a lot of sense to me.
<SPAN
class=616475318-29092003>
<SPAN
class=616475318-29092003>thanks again,
<SPAN
class=616475318-29092003>
<SPAN
class=616475318-29092003>dave
<BLOCKQUOTE
>
<FONT face=Arial
size=2><FONT face="Courier New"
color=#0000ff size=2><SPAN
class=626242917-29092003>- the parameters I get optimizing today compensate
for transient market behaviors that will eventually end, and eventually it
will do very poorly. but if those behaviors persist, at least somewhat,
for a little while, might the system to do better than average in the short
term? if so, is constant re-optimization worth
exploring?
<SPAN
class=626242917-29092003><SPAN
class=626242917-29092003>
<SPAN
class=626242917-29092003>Lot's of things to
consider here. This is probably the real "meat" of the optimizing
issue. One of the biggies is the number of variables when you conduct
your optimizations. The fewer the variables, the less chance that
eventually an approach will do poorly.
<SPAN
class=626242917-29092003><SPAN
class=626242917-29092003>
<SPAN
class=626242917-29092003>The equity and
commodity markets are not horse races: these "bets" are not handicapped
with assigned odds. Seems to me that since all the horses in the race
are "even-money", one should chart the "form" and only bet on the ponies that
have performed the best (over the most recent period of time).
<SPAN
class=626242917-29092003><SPAN
class=626242917-29092003>
<SPAN
class=626242917-29092003>Expecting a particular
stock to test well with data from 1997 is foolish. Expecting a
particular system to trade well in 1997 is not foolish. Issues fall into
and out of patterns of accumulation and distribution. Sometimes,
supply and demand takes a trip down "random walk street". I
think it makes sense, if you have a sound approach to the markets, to
concentrate on "ranking" issues based on return. If you concentrate your
efforts on selecting issues that have consistently performed with your systems
parameters, the odds favor continued consistency. If supply and demand
changes it's character for a particular issue...you must stop trading
it.
<SPAN
class=626242917-29092003><SPAN
class=626242917-29092003>
<SPAN
class=626242917-29092003>I believe, constant
reoptimization is the way to go. What is the definition
of constant? For me, I reoptimize every quarter. Most of the
time, reoptimization does not mean a reassignment of triggers or
filters. Most of the time, it means adjusting WHAT I'm trading (adding
and subtracting issues in my universe)...not HOW I'm trading.
<SPAN
class=626242917-29092003><SPAN
class=626242917-29092003>
<SPAN
class=626242917-29092003>Please share if Dave
responds to your questions,
<SPAN
class=626242917-29092003><SPAN
class=626242917-29092003>
<SPAN
class=626242917-29092003>Take
care,
<SPAN
class=626242917-29092003><SPAN
class=626242917-29092003>
<SPAN
class=626242917-29092003><SPAN
class=626242917-29092003>Steve
Yahoo! Groups Sponsor
ADVERTISEMENT
Send BUG REPORTS to bugs@xxxxxxxxxxxxx
Send SUGGESTIONS to suggest@xxxxxxxxxxxxx
-----------------------------------------
Post AmiQuote-related messages ONLY to: amiquote@xxxxxxxxxxxxxxx
(Web page: http://groups.yahoo.com/group/amiquote/messages/)
--------------------------------------------
Check group FAQ at: http://groups.yahoo.com/group/amibroker/files/groupfaq.html
Your use of Yahoo! Groups is subject to the Yahoo! Terms of Service.
|