It looks like this is a pattern classification problem... I believe it
should be done for a set of data once and then stored. Hence you can
backtest and or optimize without this loopback in the strategy itself.

On 9/8/09, nonlinear5 <[email protected]> wrote:
>
>
> I've just noticed the references to the k-nearest neighbor algorithm
> in the paper that you posted:
>
> http://jbooktrader.googlegroups.com/web/FTW+FastSimilaritySearchundertheTimeWarping.PDF?gda=JuLanmEAAADiZ9EZTErSyovyGfFcUvJWfauvUjO6-JrkupSpGnkvjad7YgV_yHBnssshpFKvu8K8Q9IRipEW7xyvooQY7WFrFnBj3Dfd04DXptCnlConaVMJP-kItwVPBwjdKujmMDOVcV4Kf5x1iV4X6-2IalYA
>
> This should reduce the search time from O(N) to O(log(N)), I believe.
> >
>

--~--~---------~--~----~------------~-------~--~----~
You received this message because you are subscribed to the Google Groups 
"JBookTrader" group.
To post to this group, send email to [email protected]
To unsubscribe from this group, send email to 
[email protected]
For more options, visit this group at 
http://groups.google.com/group/jbooktrader?hl=en
-~----------~----~----~----~------~----~------~--~---

Reply via email to