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

Re: Re: Fuzzy Logic vs. System Dynamics



PureBytes Links

Trading Reference Links


----- Message d'origine ----- 
De : Allan Kaminsky <allan@xxxxxxxx>
À : <omega-list@xxxxxxxxxx>
Envoyé : vendredi 18 août 2000 22:27
Objet : Fwd: Re: Fuzzy Logic vs. System Dynamics


> This is a copy of a message posted to the Fuzzy Logic mailing list. Will 
> Siler is a worker in the field. I thought the topic might be of interest, 
> given the recent discussion on FL.
> 
> Note that the link given in the message didn't work for me. However,  the 
> following link is OK:
> 
> http://hometown.aol.com/wsiler
> 
> Allan
 
This is a general purpose web page ( some links are broken , but is overall readable, althought not in french).
There is an example  at the end with a moving average. anamysis applied to time series.
People who do not know anything to FL may have a look, but I'm not sure that they will understand how this can be implemented into a  trading application.

The author insists on the fact that FL application must be specifics to the problem solved.
An here is the main difficulty.
Setting this is not a piece of cake, and outside the full automated search methods, there is a lot of work before getting results that could somewhat generalize.
And I know of what I speak in this field: The very first version of the software had these basic features.
Took days and days  tos etup the rules, test , retrain , adjust the parameters.
Well, it was in 1994.-1995...
Now the same is done within minutes and with better results in most cases.

But this is a good starting point if you finally become interested in FL ( do not forget that you perform yourself FL in your brain when writing a system and attempting to find the best rules with the best parameters within a given confidence interval).

PO