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 : Neural Nets - A tool for the 90's -- Ignore unavailable to you. Want to Upgrade?

To: LastShadow who wrote (625)	8/15/1999 10:11:00 PM
From: Tim Krieg	Read Replies (2) \| Respond to of 871

LastShadow, >>>...Nets are a finishing tool, a compass, or perhaps a >>>screen. But buy itself, back-propogation mathematics >>>holds no secret. A bit off topic, but have you used nets to understand your inputs? Do you know which ones are destructive or constructive for generalizing? Have you learned from your nets what high and low correlation between inputs has on the success of a trading strategy? Some have looked at input correlation, have you looked at input importance? What a mouthful of questions, maybe some folks out in this thread have explored these areas and would be kind to comment. Tim

To: LastShadow who wrote (625)	4/4/2000 11:00:00 PM
From: xu, b.	Read Replies (1) \| Respond to of 871

>But, I understand what you are asking, and the best I can >answer that is to refine what i do - which is not to train >specifically for any one equity, but rather to screen for >candidates with potential. I don't want to know if my nets >can predict the close or % change or anything else >statistically often. I want the larger picture. Are >financial sectors moving, are tech stock heading down, are >industrials going to sustain some climb afterthe SPX drops >from net stock bombshells? Given that sort of view I can >then look for those price change leaders (again - >something the net can do well - not just how much did it >climb once, but how often and with what cycle or frequency >can it be possible to continue). Last, As usual, I am screen all the posts with my brain not an NN. Your statement above is interesting and I think it's a correct question to ask the net. I would appreciate it if you could elaborate your methodology without revealing your top secrets. I am interested in some step-by-step guidance in NN design because I am new to this stuff. Bai