SI
SI
discoversearch

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor.  We ask that you disable ad blocking while on Silicon Investor in the best interests of our community.  If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.
Strategies & Market Trends : NeuroStock
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
To: Jay Hartzok who wrote (347)11/6/1998 1:15:00 AM
From: Len Giammetta  Read Replies (1) of 805
 
Jay, I've noticed the same situation on some of the nets I modelled using only the long term filter of indices, especially the models that include WSX as a related. My WSX model has been difficult if not impossible to train. I never did achieve a crisp diagonal in the stats window. Also, 4 of the 5 stock nets I modelled using WSX as a related have been very disappointing. I didn't have any problems using RUT or COMP or any of the other 10 character indices from MI.

I was thinking that instead of removing the s/t related index from your net, maybe you could try, if you haven't already, desensitizing the model by playing with the influence setting for that related. If however, based on your observations, that stock has no history of participation in the index movement, the index should probably have not been selected as a short term related to begin with.
Report TOU ViolationShare This Post
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  

HomeMailHotSubjectMarksPeopleMarksKeepersSettings
Terms Of UseContact UsCopyright/IP PolicyPrivacy PolicyAbout UsFAQAdvertise on SI
© 2025 Knight Sac Media.  Data provided by Twelve Data, Alpha Vantage, and CityFALCON News