: amibroker@yahoogroups.com
Subject: RE: [amibroker] Re: Fitness Criteria that incorporates Walk Forward
Result
On the question of defining fitness as a time series. I agree that having a
value every bar wouldnt be useful
However Looking at the following scenario, using CAR as an example
If we
: [amibroker] Re: Fitness Criteria that incorporates Walk Forward
Result
Greetings all --
I agree with Fred's comments just above this posting.
On the subject of calculation of an objective function. In my opinion, it is
important to consolidate all of the characteristics that are importa
://www.amibroker.org/userkb/2007/08/13/4-io-robustness-a-sensitive-subje
ct/
_
From: amibroker@yahoogroups.com [mailto:[EMAIL PROTECTED] On Behalf
Of Howard B
Sent: Friday, May 09, 2008 1:46 PM
To: amibroker@yahoogroups.com
Subject: Re: [amibroker] Re: Fitness Criteria that incorporates Walk
Greetings all --
I agree with Fred's comments just above this posting.
On the subject of calculation of an objective function. In my opinion, it is
important to consolidate all of the characteristics that are important to
you (remember -- the definition of this function is your personal choice)
i
1. The logic behind having a sensitivity guided or influenced in sample
optimization is . Less sensitive parameters = A more robust system = A
higher likelihood of good performance OOS . The problems with a separate
guidance phase or a Test OOS that precedes a Real OOS is that by definition
th
: amibroker@yahoogroups.com [mailto:[EMAIL PROTECTED] On Behalf
Of Howard B
Sent: Thursday, May 08, 2008 11:34 PM
To: amibroker@yahoogroups.com
Subject: Re: [amibroker] Re: Fitness Criteria that incorporates Walk Forward
Result
Hi Brian --
I tend to agree with Fred. I, personally, do not use the
Hi Brian --
I tend to agree with Fred. I, personally, do not use the guidance data
set. If you want to use it, and you are looking for consistency between the
two data sets, that might be valuable. But another measure of that is
simply the equity curve and other performance stats over both peri
Personally I couldn't find any value in the guidance phase which I allowed
for in IO for a couple of years and have since removed the capability.
_
From: amibroker@yahoogroups.com [mailto:[EMAIL PROTECTED] On Behalf
Of brian_z111
Sent: Thursday, May 08, 2008 8:32 PM
To: amibroker@yahoo
Greetings all --
I am coming to this discussion a little late. I just returned from giving a
talk at the NAAIM conference in Irvine. Some of the discussions I had with
conference attendees was exactly the topic of this thread.
If you are using some data and results to guide the selection of log
thanks. Will have a look,
Ed
- Original Message -
From: Fred
To: amibroker@yahoogroups.com
Sent: Thursday, May 08, 2008 5:42 PM
Subject: [amibroker] Re: Fitness Criteria that incorporates Walk Forward
Result
There's a simple example of this in the UKB under Intelligent
hi,
"While optimization can be employed to search for a good system via
methods utilizing automated rule creation, selection and combination
or generic pattern recognition"
anyone care to explain how this works? Some kind of inversion technique? Here
is what I want now give me the rules to g
Paul,
Let's take this offline ... Tell me what you have in mind via email and I'll
consider it ...
- Original Message -
From: Paul Ho
Date: Wednesday, May 7, 2008 12:28 pm
Subject: RE: [amibroker] Re: Fitness Criteria that incorporates Walk Forward
Result
To: amibroker@yahoo
During in sample optimization Fitness is adjusted for sensitivity if users
direct it to be so ...
- Original Message -
From: Paul Ho
Date: Wednesday, May 7, 2008 10:26 am
Subject: RE: [amibroker] Re: Fitness Criteria that incorporates Walk Forward
Result
To: amibroker@yahoogroups.com
amibroker@yahoogroups.com
Subject: RE: [amibroker] Re: Fitness Criteria that incorporates Walk Forward
Result
Paul,
One other word of caution .
If you are using OOS testing to drive the selection process of parameters to
be used in sample then you run the risk of invalidating the OOS.
Fred
Fitness is adjusted for sensitivity isnt it? even though it doesnt prelude
it.
_
From: amibroker@yahoogroups.com [mailto:[EMAIL PROTECTED] On Behalf
Of Fred Tonetti
Sent: Wednesday, 7 May 2008 11:49 PM
To: amibroker@yahoogroups.com
Subject: RE: [amibroker] Re: Fitness Criteria that
Paul,
One other word of caution .
If you are using OOS testing to drive the selection process of parameters to
be used in sample then you run the risk of invalidating the OOS.
I could have automated this process in IO but I didn't for exactly this
reason.
_
From: amibroker@
Paul,
Sensitivity analysis during in sample optimization is not directly related
to finding a new fitness high.
That would be too restrictive and might well preclude finding solutions that
have better fitness after being adjusted for sensitivity.
_
From: amibroker@yahoogroups.c
17 matches
Mail list logo
