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: Bill Scoggin who wrote (524)	12/28/1998 12:56:00 PM
From: Len Giammetta	Read Replies (1) \| Respond to of 805

<Neurostock is designed to predict about 10 days ahead> Actually, if I remember correctly, Neuro is trying to predict what will happen within the following 10 day period. However its sensitivity is somehow dependent on the trading strategy and I think influence settings. I've been keeping its signals on my portfolio from day 1. Generally, at least the way I seem to be setting up my models, I get a premature buy signal, sometimes up to 5 days, but the sells are unpredictable, many times the occurring next day. As a result, to maximize profits, and minimize the risks, I use other indicators to time entry into and out of stocks that Neuro selects. usually it works rather well. Just one guys opinion.

To: Bill Scoggin who wrote (524)	12/28/1998 1:13:00 PM
From: Jay Hartzok	Respond to of 805

Bill, If you have a good net, Neuro is usually right at some point in time within the 10 day time frame. I remember awhile back, Len posted that he had taken a position in a stock and the price started to decline. It went past his acceptable loss point and he sold at a loss to stop the bleeding only to see the price rebound a few days later to a point where he could have sold for a gain. So actually his net was accurate. I've had the same thing happen, so he is not alone in this respect. Sometime ago I tried to make nets that would predict one to three days ahead. This was when I was using both general market and industry indices for relateds. I shortened the s/t filter to two and three days and used one day for all other inputs. The results were less than desirable. I haven't tried it since I started using only industry group indices for relateds. I may try it again using these relateds and see how it does. If I have any success, I'll let you know. Jay