In this issue:
I. Announcing the new Fuzzy Sets add-on
II. The Tax Deduction Sale ends April 15
III. Meatballs
IV. eSignal 7.6 problems
V. Let the experts find a formula for your data mining problem
VI. “Stikky Stock Charts” by Lawrence Holt Books
VII. AI College class extended
VIII. A plea from our Technical Support department
IX. Make sure you continue to get the news
*******************************************************
I. Announcing the new Fuzzy Sets add-on
You’ve asked for it, and now it is here: the Fuzzy Sets add-on for NeuroShell Trader Professional and DayTrader Professional.
Fuzzy logic was invented by L.A. Zadeh and further popularized by Bart Kosko. Fuzzy logic is not some theoretical idea that has yet to catch on. By 1990 the Japanese had over 100 real fuzzy control applications and products. The city of Sendai in Japan has controlled its subway with fuzzy logic since 1988. General Motors’ highly successful Saturn applies fuzzy logic for automatic transmission shift control. Duke University engineers have shown that intentionally imprecise rules of thinking can help hotel computers sell the right room to the right customer at the right time, thus boosting income.
Ward Systems Group introduced what we believe was the first commercial trading software to allow users to describe price movements with fuzzy logic statements (the Fuzzy Pattern Recognizer add-on). A user could essentially give NeuroShell instructions such as:
“Find patterns where the price rose, then dropped, then dropped sharply, then rose sharply.”
The new Fuzzy Sets add-on is somewhat different in that it allows users to describe a combination of values of traditional indicators with fuzzy logic. With Fuzzy Sets the user can instruct NeuroShell with functions equivalent to fuzzy statements like:
“Buy when the Stochastic %K indicator is very high, and the Commodity Channel Index is high, and the spread between two moving averages is low.”
Contrast that with the typical trading utilization of an indicator is to make decisions based upon rules like whether that indicator (let’s say the Stochastic %K) is above or below some threshold. For example:
Buy when the STOCH%K > 70 and sell when the STOCH%K < 40 Those 2 rules above are sometimes called "crisp" rules, because they "break off" suddenly. In the last rule above, you are buying when the STOCH%K is 70 but not when it is 69. A human might still give consideration to buying when the STOCH%K reached 69, or even at a level of 65, although he would not consider it as strong as a buy as when STOCH%K = 70. In fact, a human would probably consider STOCH%K=80 to be a much stronger buy signal than STOCH%K=70. Fuzzy rules are a little different than crisp rules in that they do not break off suddenly. Let's consider the following example, where we will use the STOCH%K again. Suppose we have decided that STOCH%K can be considered to be in one of 5 categories or "fuzzy sets": 1. very low 2. low 3. medium 4. high 5. very high Then we could create "fuzzy" rules such as one of these two: Buy when STOCH%K is high and sell when STOCH%K is very low. Buy when STOCH%K is very high and sell when STOCH%K is medium. Actually the Fuzzy Sets add-on does not really use fuzzy words like low, very high, etc. For one thing, instead of just 5 fuzzy sets (very low, low, medium, high, and very high) you can have 10 or 20 or even more if you like. So instead of words, we use 1 for the lowest, 2 for the next lowest, etc. on up to the highest range. Of course, most people will have no idea what fuzzy set you should be looking for in order to buy or sell, so that's where the NeuroShell optimizer comes in. The optimizer will decide the total number of fuzzy sets, and which set you should have for a long entry, long exit, short entry, and short exit. Our Fuzzy Sets indicators can be used in Trading Strategies as well as neural nets. We have some that do a Fuzzy-AND of up to 10 fuzzy indicators, and other that do a Fuzzy-OR of up to 10 fuzzy indicators. The Fuzzy Sets add-on is ready now and is $299 (US) by Internet download, but if you act to purchase before April 15, you can take advantage of a 15% discount sale (see item 2), making the price only $254.15. The software comes with a help file, 5 examples, and 38 fuzzy indicators. ******************************************************* II. The Tax Deduction Sale ends April 15 As those in the United States head into tax season, there is a mad rush to dig up paperwork, find receipts, get W2's, 1099's, or some other numerically named form, so we can make sure we avoid the dreaded audit. During this process, we also try to squeeze out every last deduction that we can find. While there isn't much you can do to get any extra deductions for the 2003 tax year, we want to help you out for 2004. Since the US Government allows you to deduct the cost of tools used for investing (consult with your accountant to make sure you can), why not use the NeuroShell Trader Series? To help you out in case you did not have enough tax taken out and have to pay in more, we are going to take 15% off of the list prices of the NeuroShell Trader, NeuroShell Trader Professional, NeuroShell DayTrader Professional and all the add-ons. We will even apply the discount to upgrades as well. The discounted prices will NOT show on the price lists and ordering forms found on our website site, but rest assured, the discount will be taken off your order before processing your method of payment. This sale ends April 15, 2004. No filing of form 2350 for an extension either! Absolutely no exceptions, no rainchecks, no waivers, no applying the special to previous orders and this offer cannot be combined with any other discounts or offers. ******************************************************* III. Meatballs Jixian Zhang of the Jiangsu University of Science and Technology in China and G.S. Mittal of the University of Guelph in Ontario, Canada have trained artificial neural nets (ANN) to make predictions of the temperature, moisture, and fat content of meatballs during the deep-fat frying processes. Among some of the numerous input variables were: frying time, meatball radius, initial moisture content, initial meatball temperature, and oil temperature. The net, using our NeuroShell software, was trained and verified to produce outputs including: temperature at meatball geometric center, average temperature of meatballs, average fat content of meatball, and average moisture content of meatball. They found the hidden neurons behind the neural net to produce minimal error in generating outputs, and were pleased to ascertain via NeuroShell which variables had the most and least influence within their predictions. As a result of their research, they found that "trained ANN can be used to predict outputs . . . with high precision." They concluded, "predicting meatball deep-fat frying process by ANN using simulation data is a simple, convenient and accurate method. Prediction errors could be reduced by careful selection of hidden nodes and appropriate combination of learning rate and momentum . . . . The ANN model can be used in food process control for its accurate prediction results and real-time fast response." Their paper, "Prediction of Temperature, Moisture and Fat Contents in Meatballs During Deep-Fat Frying Using Artificial Neural Network" was published in Proceedings of 99 International Conference on Agricultural Engineering in Beijing, China, December 1999. (Yes, sometimes it takes Ward Systems a while to find out about the papers people write!) Our question: What about the spaghetti? ******************************************************* IV. eSignal 7.6 problems Some of you who have installed eSignal 7.6 have experienced problems when NeuroShell tried to connect. It seems that users who never had eSignal 7.5 are especially affected. eSignal made changes that affected many third party vendors, not just Ward Systems Group. Unfortunately, eSignal did not provide an advance version of 7.6 for third party vendors to test, so the compatibility failures were as much a surprise to us as they were to you. However, after working with eSignal now for a couple of weeks on this, we think the problems are close to being solved. Watch the Bugs, Fixes, and Warnings portion of www.ward.net for news on this issue. ******************************************************* V. Let the experts find a formula for your data mining problem We've had some confusion regarding our new Formula Detective (SM) Data Mining Service and thought we would set the record straight. This is data mining with a plus - you get a formula that relates the significant variables from your database. Another plus is that we do the work for you. You don't have to know anything about modeling, data mining programming, etc. to get the formula. Send us your data and we analyze it and apply the knowledge we've gained from over 16 years of working with modeling, neural networks, genetic algorithms, and fuzzy logic to the task. The results will be a data mining formula that provides new insight into your sales forecast, process control, chemical formulation, or other modeling problem. You also receive a rating for the effectiveness of the variables in the data. It also won't cost you a bundle to investigate whether this service is right for you. There will be a modest non-refundable deposit, but beyond that you won't have to pay for the service unless you like the results the formula provides. Check out www.formuladetective.com for the latest information. ******************************************************* VI. "Stikky Stock Charts" by Lawrence Holt Books The following book is a very understandable source of information for indicators like trendlines, channels, medium term, long term, support resistance, head and shoulders: "Stikky Stock Charts" by Lawrence Holt Books, October 2003, distributed by Four Walls Eight Windows, New York, NY 10011. Stikky Stock Charts is one of a series of books that uses a graphic learning method to teach concepts in an easy to follow, step-by-step approach. This particular book in the series teaches anyone the signals that professional traders use to make buy and sell decisions. Sequence One of the book tells you how to identify trends and draw trendlines, support lines, and resistance lines. While you cannot actually draw these patterns using the NeuroShell Trader, you can print out charts from the Trader and draw the described lines. That way you will understand the background behind many indicators that are usually drawn instead of inserted in analytic tools like NeuroShell. Overall the book is an excellent resource for learning the background and meaning behind several of the indicators included in the NeuroShell Trader without getting bogged down in math formulas. Best of all it is only $12 US at this time. To learn more, visit www.stikky.com or call (646) 375-2974. ******************************************************* VII. AI College class extended The current AI college class will be extended until the end of April. We have done this in order to let some attendees who signed up in March finish the course. Therefore, if you were one of those who wanted to take the class during April, you can now do it if you get started soon. This is an online advanced course taught by Steve Ward for NeuroShell Trader Professional and DayTrader Professional. See www.aicollege.com for details. ******************************************************* VIII. A plea from our Technical Support department Lately, a few users have emailed questions or problems and then called within a very short time after emailing. This often happens on Mondays and Fridays, which are the two busiest days for us. The email plus the call is very counter-productive for us, which in turn, will become counter-productive for the rest of our users including you at some point. Rest assured that we answer every single email that comes in, in the order in which we receive it, unless it requires some deeper investigation. Emails are normally answered within 24 hours from which we receive it during the time our office is open. This means that if you send an email to us Sunday at 2:00 PM, we won't have a chance to look at it until Monday at 9:00 AM, at which time we are loaded with emails from the weekend. Many times, emails are answered within an hour or so, but not Monday morning. So, please do us a favor. If you email something in to us, don't call unless it has been more than 24 hours or unless it is a dire emergency (even then, please mention the email you already sent). ******************************************************* IX. Make sure you continue to get the news We are still surprised that, many months after we sent out our June newsletter announcing release 4.0, users are still calling or emailing to ask when release 4.0 will be available. Seems they all changed their email addresses and never notified us of that. They could have been making money with the new features all of this time. There are many others, no doubt, who still don't know about release 4.0. After all these years we are also still getting tech support calls from NeuroShell 2 users who don't know about the AI Trilogy and its components. So they're stuck trying to impress their bosses with older technology. Don't be left behind - tell us when you change email addresses. *******************************************************