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 (770)	4/18/2000 10:37:00 PM
From: xu, b.	Respond to of 871

Dan, "The model posted is merely an example. It has held up well for what it was designed to do. Biocomp doesn't actively research what underlying forces drive the market. They just build software." Fair enough. But they may want to make it more attractive for this PR thing. "Perhaps a better example of what can be done with Profit can be found at Daniel Wilson's site, wildcattrader.com. He seems to catch the swings within a day or two." Very interesting. I need more time to gain confidence in someone else's prediction especially when I don't know what he is predicting. I am wondering if he uses sort of intraday data to spot these exact turning points. His VPF oscillates too fast and can can only be remotely related with his smooth signal unless ANN and GA can do something magic that I don't know. "It has a classification option which may work. " Excellent point. In my view, classification is easier than prediction. ANNs are suppose to do classification and prediction. Once the models are trained, it takes only a fraction of a second to calculate a neural indicator and/or do a classification. I am asking classification: bullish, bearish and neutral (Just a quick comment: being able to do nothing is very important for a trader. Lots of people like actions that's why day trading is so attractive. I like managed position trading. I guess this is what LastShadow is doing as well.) It seems TSOM is the way to go for classification. Has anybody made some progresses on TSOM model? I like BP, CATNN and TDNN for prediction. Can NS trader do the same thing? Bai

To: Optim who wrote (770)	4/21/2000 2:26:00 PM
From: Larry Livingston	Read Replies (1) \| Respond to of 871

Optim, You've mentioned the Wildcattrader site many times. I've checked his sight out and even bought some of the books he mentions. I'm always a little skeptical of sites that promise the world but I must say I was intrigued both his site and the books on harmonic resonance. When you say he's pretty good is that based on your actually subscribing to his service and following his signals real time or is based on the delayed posted results? Larry PS If you are a subscriber can say that the past history is the same as the real time. In others words is the modelcurve fitted and updated with time or has it been the same model for the entire time period which would be quite an achievement?