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: Gary E who wrote (16899)	2/27/1999 1:18:00 PM
From: Brian Hornby	Read Replies (1) \| Respond to of 44573

I use Profit (http://www.biocompsystems.com), as do Robert and Patrick on this thread and some others in the Neural net thread. Look up Optim's comments in the neural network thread, he has looked at all the systems and seems to know a lot. I use it to predict the e-mini and it goes long and short. I had to play with different inputs etc before getting the sequence I am happy with. I found averaging the predicted output helped kill a lot of the short term whipsawing and was more profitable. I also use a lot of sentiment and other indicators (put/call, interest rates, Yen) as well as some technical indicators based on the SP. Neural net generated models can be losing as well, and if they win in the past obviously they can lose in the future and in fact are known to fall apart at some point. The 12 winning trade model I generated and used data after the Nov 20 date as out of sample data. It had 8 trades when I generated it a couple of weeks ago. All the other models I started looking at the same time have remained profitable as well.