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: Brian Hornby who wrote (40019)	12/1/1999 12:29:00 PM
From: F Robert Simms	Read Replies (1) \| Respond to of 44573

Oops! Sorry about that. I zoomed in to get a closer look and forgot to move it to the right before I pasted it. I will correct it tonight. All of the data shown is in sample data. This is a description of my net. The posted net is a collection of nets. Each component net was built without any data from the last few months. This makes the components pure. I then optimized the collection and only choose the ones that were good and different from each other (Optimize Ensemble). This added some curve fitting, which contaminated the composite model. I then tweaked it a bit more buy adding and deleting each model, from the original collection, one at a time to see if the total earnings improved. This added even more contamination and curve fitting. I am in the process of doing it again for December so look back at it in a few days to see a fresher model. The inputs are mostly intermarket, breadth and sentiment data. What kind of candlestick oscillators do you have? Ok if it is propriatory. Best Wishes, Bob