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 : Systems, Strategies and Resources for Trading Futures -- Ignore unavailable to you. Want to Upgrade?

To: Robert Graham who wrote (15527)	2/15/1999 2:27:00 PM
From: peter n matzke	Read Replies (1) \| Respond to of 44573

cse.ogi.edu reading material on neural nets

To: Robert Graham who wrote (15527)	2/15/1999 3:08:00 PM
From: Vitas	Respond to of 44573

In broad terms I think the point is that any system, whether neural or not, has to have filters for trending versus trading range markets. Vitas

To: Robert Graham who wrote (15527)	2/15/1999 4:20:00 PM
From: F Robert Simms	Respond to of 44573

So in broad terms what you are saying is that neural net based trading breaks down when the market changes and requires a different approach to trading. At this point in time, a new model needs to be created. However, when a neural net has been built and proven for a given market, then good profits can be made. This period of profit making can last for months. Yes. I think that models can be built that will be general enough to handle most markets, but they wouldn't be optimal for any. I would probably toss them out in favor of one that is making a lot of money now and has had a good return for the last three years. People have said that, sometimes, older models will come back into making money when the market repeats. Finally, not all types of models work with the neural net approach to the market. That is a question that I can't answer. By the way, thank you for your up front and honest description of your experiences with neural nets. Thanks:) Best Wishes, Bob