Neural Nets - A tool for the 90's Message Board

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

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next

To: current trend who wrote (6)	12/8/1997 2:54:00 PM
From: Optim	Read Replies (2) of 871

>Neural Nets ---- what are they realistically capable of >accomplishing? Realistically? The best you can hope for is to design a system that will better your odds of a good trade. If you can build a system that is right 55+% of the time, that is usually good enough to make you money. Anyone that thinks that a neural net can predict a stock or market 100% of the time is deluding themselves. However, it only takes a slight tilt of the scales in your favour to be profitable. Markets are very much unpredicatable. No matter how good your system is, whether it is mechanical, TA, NN, or some other method, markets are driven by news and crowd psychology. But if a NN can pick up patterns based on what it 'recoginizes' from previous patterns, it may offer some insight and predicatbility as to what will happen in the future. >Any URL's or commentary that address this would be greatly appreciated! Try www.trendysystems.com. They have built a system using a Ward Systems group package called Neuroshell. I believe their S&P500 futures systems averages 20 points profit per month on a one contract investment. Optim

Report TOU Violation

Share This Post

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next