[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: Objective functions (was RE: [amibroker] Re: Optimization -- again)



PureBytes Links

Trading Reference Links










Hi Dave –

 

I believe that choice of objective
function should be made at an early stage of both trading and investing,
whether technical analysis or fundamental analysis is used to make buy and sell
decisions.  

 

I feel that the choice of objective function
is very personal.  For my own case, and for many trading companies,
avoidance of drawdown is very important.  The easiest way to avoid
drawdown is to make no trades, so the objective function needs a component of
return.  Other people and other companies who trade a lot of systems in a
lot of markets expect the diversification to handle drawdowns on a portfolio
level, so return is most important.  

 

If, after running your auto-optimization
routines using profit per bar, you are comfortable trading the stock and
parameters that are number one on the optimization list, then your objective
function is fine.  If you regularly look down the list and see one of the
other alternatives as more attractive, then your objective function needs an
additional component.

 

The list of potential objective function
components is quite long – total return, return per bar, drawdown, sensitivity
to small changes in parameters, holding period, trading frequency, commission
cost, percentage exposure, percentage winners, etc.    

 

Howard

 



-----Original Message-----
From: Dave Merrill
[mailto:dmerrill@xxxxxxx] 
Sent: Sunday, October 19, 2003
5:59 AM
To: amibroker@xxxxxxxxxxxxxxx
Subject: RE: Objective functions
(was RE: [amibroker] Re: Optimization -- again)

 



<span
>interesting as
usual howard (:-). one piece I wanted to drill into a bit.





 





<span
>I wonder what the
effect of using performance measures that concentrate on certain things at the
expense of others actually is. 





 





<span
>for example, my
auto-optimization stuff currently uses simple profit per bar to choose
parameter values. my gut-level assumption was that since it was ignoring
drawdown (among other things), the resulting systems might have higher drawdown
than I was comfortable with, but that profit per bar should be as good as the
trading method could produce.





 





<span
>maybe that's not
the case. maybe by choosing a more balanced success metric, not only would the
other factors not considered by my simplistic first pass metric be improved,
but profitability might be improved as well.





 





<span
>is this something
you've investigated or thought about? anyone else?





 





<span
>dave





Note &#8211; it is perfectly valid to have
different objective functions for different purposes.  For example, I
might be modeling the behavior of a sector, say oil services, with the intent
of trading individual stocks based on what I learn.  In this case, I want
to identify periods of rising prices with careful attention to turning points,
but without much interest in overall profit.  On the other hand, I might
be modeling individual high beta tech stocks, in which case my model includes
several stop loss techniques and I care most about avoiding drawdowns.

Thanks,

Howard



<font size=3
face="Times New Roman"> 


 
  
  <font size=2
  color="#003399" face="MS PGothic">Send
BUG REPORTS to <span
 >bugs@xxxxxxxxxxxxx<font
face="Courier New">
Send
SUGGESTIONS to suggest@xxxxxxxxxxxxx<span
>
-----------------------------------------<font
face="Courier New">
Post
AmiQuote-related messages ONLY to: <font size=2
 face="Courier New">amiquote@xxxxxxxxxxxxxxx<font
size=2 face="Courier New"> <font
face="Courier New">
(Web
page: http://groups.yahoo.com/group/amiquote/messages/)<font
face="Courier New">
--------------------------------------------<font
face="Courier New">
Check
group FAQ at: <a
href="">http://groups.yahoo.com/group/amibroker/files/groupfaq.html<font
face="MS PGothic"> 

Your
use of Yahoo! Groups is subject to the <a
href="">Yahoo! Terms of Service.<font
face="MS PGothic"> 













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.