Don't misunderstand me . I didn't suggest there would be any benefit to
using IO for what would be a 75 step exhaustive search optimization over
using something built into AB . When I said ANY that's exactly what I meant
.

 

  _____  

From: [email protected] [mailto:[EMAIL PROTECTED] On Behalf
Of Ken Close
Sent: Tuesday, August 12, 2008 1:27 PM
To: [email protected]
Subject: RE: [amibroker] Optimizing Rotational - Curious Result

 

Steve--thanks for the added insight, and for the link. Looks interesting,
and I will dl and try it.

 

Fred--obviously.  I was just mucking around and wanting to "compare".
Clearly the comparison was ill structured.

 

Getting geared up for some extensive optimizations.  Will get back into your
latest IO update, again for comparison purposes.

 

Ken

 

  _____  

From: [email protected] [mailto:[EMAIL PROTECTED] On Behalf
Of Steve Dugas
Sent: Tuesday, August 12, 2008 1:07 PM
To: [email protected]
Subject: Re: [amibroker] Optimizing Rotational - Curious Result

Hi Ken - FWIW, on the opts I am doing with CMAE ( using 31 runs ), the
progress bars says I have 1.5 billion opt steps and will take over 5 years
to run, but it always converges within 10 minutes or so and often quicker. I
would just let it run, at least for say, 30 or 60 mins, you will probably
find that it finishes even quicker.

 

Oh BTW, I think you were recently looking for something that handles huge
CSV files?  I found this a couple of days ago, looks very good, apparently
does everything, it's free, supposedly spyware-free, was going to try it
before I recommended it to you but haven't had a chance yet. But as long as
I am writing anyway here it is...

 

http://www.snapfile <http://www.snapfiles.com/get/csvdb.html>
s.com/get/csvdb.html

 

Steve

----- Original Message ----- 

From: Ken Close <mailto:[EMAIL PROTECTED]>  

To: [EMAIL PROTECTED] <mailto:[email protected]> ps.com 

Sent: Tuesday, August 12, 2008 12:30 PM

Subject: RE: [amibroker] Optimizing Rotational - Curious Result

 

I stopped the optimization after several minutes. The est time was
increasing as I watched.

 

TJ said this was a trivial case which the cmae was not designed for.

 


  _____  


From: [EMAIL PROTECTED] <mailto:[email protected]> ps.com
[mailto:[EMAIL PROTECTED] On Behalf Of cstrader
Sent: Tuesday, August 12, 2008 9:56 AM
To: [EMAIL PROTECTED] <mailto:[email protected]> ps.com
Subject: Re: [amibroker] Optimizing Rotational - Curious Result

But did the cmae approach actually increase or decrease the time when you
ran it?

 

 

----- Original Message ----- 

From: Ken Close <mailto:[EMAIL PROTECTED]>  

To: [EMAIL PROTECTED] <mailto:[email protected]> ps.com 

Sent: Tuesday, August 12, 2008 9:19 AM

Subject: [amibroker] Optimizing Rotational - Curious Result

 

I thought this was a curious development---I wondered if it was possible to
optimize a rotational model.  Of course it is.

 

To test, I stuck three variables into a fairly long afl code (complex
positionscore calculations).

Raw optimization said 75 steps, estimated time ~ 4 minutes.

 

I added the cmae engine statement at the beginning and the optimize screen
said 9662 steps with est time of ~ 6 hours.

 

I thought the "cmae" optimization step would decrease time, not increase the
time so dramatically.

 

What do you think was going on?

 

Have any of you optimized a rotational strategy?

 

Ken

 


  _____  

I am using the free version of SPAMfighter for private users.
It has removed 523 spam emails to date.
Paying users do not have this message in their emails.
Try SPAMfighter <http://www.spamfighter.com/len>  for free now!

Reply via email to