One other comment about NN's ... Although they may have a clue what
they are doing, the algorithms that they develop based on the data
you feed them are for the most part hidden ... This makes utilization
of them roughly equivalent to using a black box ... imho, not a great
idea, but to each his/her own ...
--- In amibroker@yahoogroups.com, "Fred" <[EMAIL PROTECTED]> wrote:
>
> Neural Nets ... Possibly but I have yet to see anyone come out with
a
> product that generates a system that does well out of sample ...
> Dakota may be the exception, but because of things I've seen that
> particular organization do in the past it is not likely I'd ever
use
> one of their products.
>
> Intelligent Optimazation ... This is not a system writer ... In
> general it is a tool to allow problems that have enough variables
> that exhaustive search would not be feasible to be optimized. IO,
> which I wrote utilizes Particle Swarm and a genetic algorithm,
> Differential Evolution to accomplish these tasks. There are many
> other features that I think are important in this product i.e. the
> capabilities to perform automated walk forward testing and have
> intelligent optimization be driven or directed by the "sensitivity"
> of the parameter values. There's a lot more to be said on this
> subject which I can't cover in a post ... I suggest you read the
doc
> that accompanies the file that TJ pointed at in the AB-TS Files
> section. In answer to your question of whether or not having a
tool
> like this affects the bottom line ... My answer is, most
> definitely ... But as with all tools, it is about how you use them.
>
> --- In amibroker@yahoogroups.com, allansn@ wrote:
> >
> > Thanks Fred,
> >
> > All joking aside,I sincerely respect your knowledge.If I may
> ask,have you or anyone else found that the integration of nueral
> nets,A.I or "intelligent optimisation" to make a significant
> difference in the bottom line??
> >
> > I ask this as I am predomnantly a derivatives trader (dispersion)
> as well as long short equity,and most of our work is on the
> fundamental/statistical side.
> >
> > When you say both are available to be run directly on AB,what
> exactly do you mean??
> > Does Ami have an add on tool,or are you referring to Biocomp
Dakota
> >
> > Thanks,
> >
> > Allan
> >
> >
> > ----- Original Message -----
> > From: Fred
> > Date: Tuesday, October 17, 2006 11:37 pm
> > Subject: [amibroker] Re: Amibroker vs. other software
> > To: amibroker@yahoogroups.com
> >
> > > Swarm Technology i.e. Particle Swarm is a different intelligent
> > > optimization process then the other ... "fancy words like
> > > 'genetic
> > > algorithms'" ...
> > >
> > > Both of which are also available to be tun directly on AB ...
> > >
> > > --- In amibroker@yahoogroups.com, allansn@ wrote:
> > > >
> > > > Hello Howard,
> > > > A pleasure to make your acquaintance...I will certainly take
a
> > > look
> > > at your book and most likely purchase it.No track record
> > > required.That was only a requirement if Fred was the author:)
> > > >
> > > > Is the book available yet??
> > > >
> > > > If you dont mind,would you give me a bit of insight into
> > > Biocomp
> > > Dakota?It seems like an interesting product,and I am clueless
to
> > > swarm technology...
> > > >
> > > > Thanks for the info
> > > >
> > > > Allan
> > > >
> > > > ----- Original Message -----
> > > > From: Howard B
> > > > Date: Tuesday, October 17, 2006 6:45 pm
> > > > Subject: Re: [amibroker] Re: Amibroker vs. other software
> > > > To: amibroker@yahoogroups.com
> > > >
> > > > > Hi allansn --
> > > > >
> > > > > I am writing a book. You can see the contents and a sample
> > > > > section of it at
> > > > > www.quantitativetradingsystems.com. The focus of the book
is
> > > on
> > > > > tradingsystem development, with examples in AmiBroker and
> Dakota.
> > > > >
> > > > > I think AmiBroker is a great platform for systems
> > > development.
> > > > > There is
> > > > > already a great deal of material available documenting
> AmiBroker's
> > > > > capability and operation. I will cover enough of AmiBroker
> > > so
> > > > > that the book
> > > > > can act as a guide. But covering every aspect of AmiBroker
> > > is
> > > > > not the
> > > > > intent of the book.
> > > > >
> > > > > Post my track record? I am not seeking funds to manage, so
> > > my
> > > > > personaltrack record is not relevant.
> > > > >
> > > > > While there will be fully functional trading systems given
> > > in
> > > > > the book, they
> > > > > will be used primarily as examples and illustrations. Some
> > > will
> > > have
> > > > > summaries of simulated trading. I expect that most readers
> > > will
> > > > > use the
> > > > > programs I provide as templates, replacing my code for
> > > entries
> > > > > and exits
> > > > > with their own. Those are the trading summaries that are
> > > important.
> > > > >
> > > > > I am well credentialed in the fields of modeling and
> > > simulation
> > > > > in general,
> > > > > and in trading system development in particular. My intent
> > > is
> > > > > to help
> > > > > persons who are interested in creating trading systems that
> > > have
> > > > > a hope of
> > > > > being profitable.
> > > > >
> > > > > Thanks for listening,
> > > > > Howard
> > > > >
> > > > > On 10/17/06, Yuki Taga wrote:
> > > > > >
> > > > > > Hi allansn,
> > > > > >
> > > > > > That would be Howard Bandy, I believe.
> > > > > >
> > > > > > Also, one could write a pretty interesting book on system
> > > > > > development, particularly highlighting the necessary
> > > metrics the
> > > > > > system would need to display to indicate effectiveness,
> > > and
> > > > > necessary> testing methodology that would verify that the
> > > > > metrics were really
> > > > > > there -- without ever claiming to have found a tradable
> system.
> > > > > >
> > > > > > Of course, it would be even *more* interesting to see a
> > > great
> > > system
> > > > > > with audited broker statements. ^_^ But it wouldn't be
> > > > > *necessary* to
> > > > > > have even one tradable system to write a very interesting
> > > book
> > > > > on the
> > > > > > subject of designing them and testing them.
> > > > > >
> > > > > > Yuki
> > > > > >
> > > > > > Wednesday, October 18, 2006, 5:16:36 AM, you wrote:
> > > > > >
> > > > > > aon> LOL.....I thought you were writing a book on
systems???
> > > > > >
> > > > > > aon> Hmmmm...I think I may have confused you with someone
> else..
> > > > > >
> > > > > > aon> Sorry Fred...
> > > > > >
> > > > > > aon> ----- Original Message -----
> > > > > > aon> From: Fred
> > > > > > aon> Date: Tuesday, October 17, 2006 3:12 pm
> > > > > > aon> Subject: [amibroker] Re: Amibroker vs. other software
> > > > > > aon> To: amibroker@yahoogroups.com
> > > > > >
> > > > > >
> > > > > > >> Without some independent third party to check the
> > > results I
> > > > > > >> wouldn't
> > > > > > >> find that to offer any additional credibility ... and
> > > ...
> > > > > Last I
> > > > > > >> checked I wasn't writing any books ...
> > > > > > >>
> > > > > > >> --- In amibroker@yahoogroups.com ,
> > > > > > allansn@ wrote:
> > > > > > >> >
> > > > > > >> > Fred,
> > > > > > >> >
> > > > > > >> > If I was authoring a book on system design and
system
> > > trading
> > > > > > >> I
> > > > > > >> would certainly post my track record.I would think
that
> > > it
> > > would
> > > > > > >> lend a boatload of credibility to the
> > > content.Otherwise,it is
> > > > > > >> no
> > > > > > >> different than marketing a system and asking one to
> > > believe
> > > the
> > > > > > >> results.
> > > > > > >> >
> > > > > > >> > However if you are writing a book on programming and
> its
> > > > > > >> application to trading,that is another story.
> > > > > > >> >
> > > > > > >> > Not trying to undress you,though you did suggest I
> > > show you
> > > > > > >> mine
> > > > > > >> and you will show me yours:)
> > > > > > >> >
> > > > > > >> >
> > > > > > >> >
> > > > > > >> > ----- Original Message -----
> > > > > > >> > From: Fred
> > > > > > >> > Date: Tuesday, October 17, 2006 11:45 am
> > > > > > >> > Subject: [amibroker] Re: Amibroker vs. other software
> > > > > > >> > To: amibroker@yahoogroups.com
> > > > > > >> >
> > > > > > >> > > I'll show you mine if youshow me yours ...
> > > > > > >> > >
> > > > > > >> > > But then there's really no need is there ? ... I'm
> not
> > > > > > >> marketing
> > > > > > >> > > a
> > > > > > >> > > system and asking you to believe the results I
> obtained
> > > > > > >> using
> > > > > > >> it ...
> > > > > > >> > >
> > > > > > >> > > As I said before ... you want to buy a platform
> > > that has
> > > > > > >> canned
> > > > > > >> > > systems ... by all means do so ...
> > > > > > >> > >
> > > > > > >> > > --- In amibroker@yahoogroups.com
> > > > > ,> allansn@ wrote:
> > > > > > >> > > >
> > > > > > >> > > > Fred,
> > > > > > >> > > >
> > > > > > >> > > > If I am not mistaken,you will be coming out with
> > > a
> > > > > book on
> > > > > > >> > > system
> > > > > > >> > > development.Judging by your post,which I am in
FULL
> 100%
> > > > > > >> > > agreement,is it safe to assume you will be posting
> your
> > > > > > >> AUDITED
> > > > > > >> > > brokerage statement for the last 5-10 years?
> > > > > > >> > > >
> > > > > > >> > > >
> > > > > > >> > > >
> > > > > > >> > > >
> > > > > > >> > > >
> > > > > > >> > > > ----- Original Message -----
> > > > > > >> > > > From: Angelo
> > > > > > >> > > > Date: Tuesday, October 17, 2006 9:46 am
> > > > > > >> > > > Subject: [amibroker] Re: Amibroker vs. other
> software
> > > > > > >> > > > To: amibroker@yahoogroups.com
> > > > > > >> > > >
> > > > > > >> > > > > --- In amibroker@yahoogroups.com
> > > > > ,> "Fred" wrote:
> > > > > > >> > > > > >
> > > > > > >> > > > > > LOL ... Anyone can make performance stats
say
> > > whatever
> > > > > > >> > > they
> > > > > > >> > > > > want ...
> > > > > > >> > > > > > Unless you've seen some vendors audited
> brokerage
> > > > > > >> > > statement
> > > > > > >> > > > > you
> > > > > > >> > > > > can
> > > > > > >> > > > > > take them with a grain of salt ... If you
are
> > > looking
> > > > > > >> for
> > > > > > >> > > an
> > > > > > >> > > > > out
> > > > > > >> > > > > of
> > > > > > >> > > > > > the box solution that makes money, you're
> > > > > dreaming ...
> > > > > > >> As
> > > > > > >> > > I
> > > > > > >> > > > > asked
> > > > > > >> > > > > > before ... If one had the golden goose, why
> > > would
> > > they
> > > > > > >> > > sell it
> > > > > > >> > > > > for
> > > > > > >> > > > > > $3k, $30k or even $300k ...
> > > > > > >> > > > > >
> > > > > > >> > > > >
> > > > > > >> > > > >
> > > > > > >> > > > > That's obvious and out of subject: nobody's
> dreaming
> > > > > > >> here,
> > > > > > >> > > > > nobody's
> > > > > > >> > > > > asking to buy the Holy Grail.
> > > > > > >> > > > >
> > > > > > >> > > > > It's just that I don't like results like those
> > > exposed
> > > > > > >> > > coupled
> > > > > > >> > > > > with
> > > > > > >> > > > > fancy words like "genetic algorithms". You
> > > might
> > > > > call it
> > > > > > >> > > > > personal
> > > > > > >> > > > > preference. By and thanks for the input.
> > > > > >
> > > > > >
> > > > > >
> > > > >
> > > >
> > >
> > >
> > >
> > >
> >
>
Please note that this group is for discussion between users only.
To get support from AmiBroker please send an e-mail directly to
SUPPORT {at} amibroker.com
For other support material please check also:
http://www.amibroker.com/support.html
Yahoo! Groups Links
<*> To visit your group on the web, go to:
http://groups.yahoo.com/group/amibroker/
<*> Your email settings:
Individual Email | Traditional
<*> To change settings online go to:
http://groups.yahoo.com/group/amibroker/join
(Yahoo! ID required)
<*> To change settings via email:
mailto:[EMAIL PROTECTED]
mailto:[EMAIL PROTECTED]
<*> To unsubscribe from this group, send an email to:
[EMAIL PROTECTED]
<*> Your use of Yahoo! Groups is subject to:
http://docs.yahoo.com/info/terms/
