Silicon Investor (SI) -- The First Internet Community

STOCKTALK

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 -- Ignore unavailable to you. Want to Upgrade?

To: CVDave who wrote (50)	9/16/1998 1:35:00 AM
From: Jay Hartzok	Respond to of 805

CVDave, I sure hope you want some company on this thread. We sure do! That's why Len and I started this thread, to get input from other users. I was beginning to think that Len and I were the only two SI members that used Neurostock. Welcome aboard. It's late and I'm tired, so I'll review your post tomorrow and submit my comments then. Jay

To: CVDave who wrote (50)	9/16/1998 2:45:00 AM
From: Len Giammetta	Read Replies (2) \| Respond to of 805

Welcome aboard... as Jay mentioned, we certainly welcome the company. You seem to have a strong understanding of the concepts involving the use and construction of the Neuro nets. Frankly, the concept of influence periods has alluded me, and there is sparse documentation to clarify the subject. Also you mentioned the verification period. Frankly, I never attempted it. How do you set it up and run it? Re: indices... I won't steal Jay's thunder since he introduced the concept to the thread, and it seems to be working as well, if not better, than using related stocks. He can explain it, and direct you to the best site to obtain the research data. I will say this though... the accuracy of the Neuro predictions can be vastly increased by using an additional indicator or two for confirmation. I also look for correlations on different indicators I construct, and on some stocks have actually, somehow, have been able to predict a couple of spikes. I believe that when this market turns around, we have the tools and experience to more than a few bucks. Again... welcome aboard. ps: Jay, to answer your question re:MCHP, I panicked, sold too early, and had my first loss this year. Subsequent to my sale, I've read numerous articles stating that the semiconductor industry is sucking wind. I wish Neuro had known that... but, I made it back with AA. Len G

To: CVDave who wrote (50)	9/17/1998 1:47:00 AM
From: Jay Hartzok	Read Replies (1) \| Respond to of 805

Dave, Sorry that I didn't respond like I said I was going to, but earlier today, I discovered some things about building nets and got confused. Talked on the phone with Len and got even more confused. Trying to sort it out now. Will try to respond tomorrow. Jay

To: CVDave who wrote (50)	9/17/1998 10:47:00 AM
From: Jay Hartzok	Read Replies (1) \| Respond to of 805

Dave, I numbered my responses according to your numbered paragraphs to keep things coherent. #1 Before I can comment on this, I need to know your definition of a "good model". That SPX net you mentioned sounds to me like it is terribly inaccurate and I'm wondering why you are still training it. #2 Not quite sure of exactly what you are doing on this subject. Please elaborate. I would like more details. #3 Through quite a lot of testing I found that using indices for relateds seems to produce more accurate nets. Most indices are used just once as long term relateds, however if a particular stock's trading patterns closely follow a particular index, I will also use it as a short term related. #4 Anytime that I ever mixed different short or long term influence periods, the net seemed to get confused, so I now maintain consistency. For all inputs I use 20 for short term relateds and normally 3 for long term relateds. As far as price and volume is concerned, if the data is in the file, I usually check the box and let Neurostock sort out the useful information. #5 I use 3 years whenever possible. Jay