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 : NeuroStock -- Ignore unavailable to you. Want to Upgrade?

To: Optim who wrote (211)	10/8/1998 7:33:00 PM
From: Len Giammetta	Read Replies (1) \| Respond to of 805

Hi Optim and welcome to the thread. I was hoping that you'd stop by and participate in our discussions. I've read your comments ( a few times to be honest with you) and have some questions. <it also means that the net has more points of failure if any of the relateds diverge from their usual relationship. > What is a "usual" relationship? Wouldn't the net learn from this "failure" and be better able to predict when it was able to relate this pattern the next time it appeared? Also, what signal do you think Neural would give if this happened... I think neutral. <This means you will get great results in the training set, but poor results during verification and real world trading.> Are you suggesting that another option when confronted with the above situation is to retrain with a different neuron setting. Do you have any theories on appropriate influence settings. Do you think it's possible to look at a historical chart of the target and the related and know from that observation which influence settings are best, or would you suggest simple experimentation until we get an acceptible accuracy? I happen to believe that simple is better, and use as few inputs as possible until I get an acceptable net. Any suggestions? <This is also why you would want to combine neural networks with other methods such as technical analysis and fundamental analysis.> I couldn't agree with you more. Neurostock seems to enpower other indicators. I like the MACD buy signal confirmation. Let's face it, when you get a buy from even the best MACD there's always the chance that it'll stall out, but my experience has been that when Neuro gives a buy and your lucky enough to get a buy on that MACD the stock takes off. Maybe I'm just lucky but I'm confident enough to bet my money on it. Optim, I don't know if you've browsed our posts but Cilia is currently working on version 3.0 and he's open to suggestions and has stated that he's willing to incorporate as many of our suggestions as possible. I know you've spent thousands of hours working with this program and would welcome any ideas that you or any of the posters volunteer. I'll be happy to accumulate them and send them to him. I've given it a little thought and have come up with a couple: 1- Include, or at least make available, some type of advanced trainer to speed up the training for all the commercial versions. 2- I'd like to see the graphical display include the option to overlay some technical indicators such as the MACD, STOCHS, and MA Crossovers to name a few. 3- Finally, I'd like to see the results include Shorts as well as the Longs.