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: Optim who wrote (670)	10/6/1999 3:47:00 PM
From: Optim	Read Replies (3) \| Respond to of 871

All, This forum has been pretty much dead for the last few months. I'd like to revive it and I will try to start posting some of my methods and research here for others to try. Is there anyone still here that would be interested in doing the same? A while back Carl R. and I exchanged ideas and signals for a few months. Some of the my best models and ideas came out of that exchange. I'd like to start this forum up again as I start to have more time on my hands. Work has died down a bit and I will be concentrating more on my trading and system development. If anyone is interested in joining in, please speak up! Optim

To: Optim who wrote (670)	3/28/2000 12:12:00 AM
From: xu, b.	Read Replies (1) \| Respond to of 871

>FWIW, I find it much easier to model on a weekly basis. >Some of the best nets I have ever developed for the S&P >are weekly traders. >Optim I would like to thank Lastshadow for bringing me here. It's an informative forum and has been a little bit dead recently. Just want to offer my 2cents here: By using weekly data, you already use a filter to filter out the daily fluctuation. You will have a cleaner data set for your NN to understand. NN is nothing but a brain function modeling tool and it's a very primitive one so it needs some helps. I am in a buisness to make structural simulation of human brain which is much more complex. Having said that, I do believe ANN is a very powerful tool and it's so powerful that one can easily fall into curve fitting if one is not careful. I have little knowledge in ANN development, however, my data analysis and trading system develpment experiences seem to suggest that if an NN is only good for one stock or one future contract, it's probably a dangerous beast. Robustness test is one the keys for a good trading system. Bai