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 (61)	3/16/1998 3:31:00 PM
From: Optim	Read Replies (1) \| Respond to of 871

All: Well it has been a while since I last posted, so I just wanted to let people know that I am still working away at the nets. I have tried to brush up on my technical analysis skills first though, as a good trader can use a net much better than someone who is new to the markets. I have also been working on stock screens (finding good picks out of a sea of stocks) that are based on TA and some fundamentals. I would base it more on fundamentals, but I don't know of any data vendors that supply fundamental data for Canadian stocks right now. Anyone know of any? My hope at this point is to find a few good stocks that work well with the nets so that I can trade them in my RRSP (Canadian version of an IRA). So the SP500 net is on the backburner right now. Guess that's it. Anyone else using neural nets, GA's, or any other tools that they care to share about? Optim

To: Optim who wrote (61)	3/30/1998 3:56:00 PM
From: JKB	Read Replies (1) \| Respond to of 871

I am interested in the S&P system since you last posted the performance. I also use NNets to predict short/med. term S&P moves(5days-2mos). I think that you correctly realized that the 137.48 point profit you experienced at the end of Oct. should be discounted from your system expectations as it was unusual. I think you should take that thinking a step further and assume that your system would have been on the WRONG side of both moves (subtract another 137.48 from your net). What are you left with? The reason that your system was on the correct side of those moves is that it was trained on them. This is good and bad. Obviously those moves account for a lot of prediction error, so when the net is training it gives a lot of weight to getting that week right, possibly at the expense of the rest of the time frame tested and trained. My suggestion, train your net without that week (remove it from the data files, test around it, or smooth it to a more normal week). NNets and other mechanical systems predict based upon recurring normal patterns, that was not a normal week! Only experience, luck, and lots of research can possibly position you properly for a market event. Best bet, if you make good money trading on normal days, take a vacation on abnormal ones, you wont make THE BIG trade, but you wont be on the wrong side either. This is my experience, I was trading that week, and the only reason I came out with a profit was a good start(long SPX puts)and luck.