I. Prediction of Long Term Responses to HIV Infections from Short Term Measurements Using Neural Networks
This sounds like a paper from a leading cancer researcher, right? No, it’s a high school science fair project!
In the Frederick County Maryland 2002 Science Fair, high school student Jennifer Gee won the grand prize and a trip to the 53rd International Science Fair with this project. The project also won first place in the Computer Science category.
“You’ll be happy to hear that I used your AI Trilogy to make predictions on the efficiency of HIV drug treatments”, Jennifer told us. “This is the same project that I worked on in the summer with Dr. Dimitrov.” Dr. Dimitrov is a leading researcher at the NIH Frederick Cancer Research Center.
Jennifer was also awarded an Excellence in Computer Science Award from Intel, a U.S. Army Achievement Award, a U.S. Navy and Marine Corps award, a US Dept. of Health Award, and also a Yale Science and Engineering award.
In May 2002 Jennifer went on to compete in the international science fair in Louisville, Kentucky. There she won two prizes from the special awards sponsors. She received a $1000 award from the Association of Artificial Intelligence, and $200 from the Association of Computing Machinery.
We should point out that this is not the first time Jennifer has won in the county science fair. In fact this is the third year in a row she has won at least first place in her category. Each year she has had a different project, but all used the AI Trilogy.
*******************************************************
II. Ward Systems Closed July 4 and 5
Our offices will be closed July 4th and 5th in celebration of Independence Day. Please plan accordingly.
*******************************************************
III. Featured Product – AI College Advanced Class
>From time to time we have held advanced seminars in the NeuroShell Trader Professional and DayTrader Professional. Our users have said they enjoyed those seminars, but not everyone seems to be able to get away from home and office for a week (2 days of travel and 3 days of class). In response to that we converted our seminar to an online class where you can study in the privacy and convenience of your home or office any time of day you like.
These online classes feature the same material and same instructor (our CEO Steve Ward) giving the lectures and answering the questions. The only differences are that the lectures are from sound files on a CD, the questions and answers are on a special forum, and the examples are on web pages and video files on the CD. You get the same amount and quality of instruction, and you pay half of what we charged for an in-person seminar.
We send you a CD containing all of the audio and video files, and they can be used after the class ends. The CD also contains a special web browser so that in one program you can view the lesson slides, play the audio lectures, play the video examples, and interact on the forum.
If you have any further questions, call our sales department (301-662-7950) or visit www.aicollege.com where you will even find a sample audio clip you can download.
Our current class runs until the end of July, so you’ll have plenty of time to take the lessons if you sign up in the next week or so. If you want to keep the materials after the class, you can do so, just remember to print off all of the web pages while you are enrolled. Then you can play the audio and video files in the Microsoft Media Player 7.
Here is the class syllabus:
Chapter 1 – Indicators
Lesson 1 – Building Advanced Indicators*
Lesson 2 – Saving Custom Indicators*
Lesson 3 – Issues with Fundamental Indicators
Chapter 2 – Simple Trading Systems
Lesson 4 – How to Build a Trading Strategy*
Lesson 5 – Simple Traditional Trading Systems*
Chapter 3 – Neural Net Prediction Systems
Lesson 6 – Choosing What to Predict*
Lesson 7 – Choosing Inputs*
Lesson 8 – Steve Ward’s Favorite Inputs*
Lesson 9 – Overview of Walk Forward Testing*
Lesson 10 – Walk Forward Testing Considerations
Lesson 11 – Training Sets and Evaluation Sets
Chapter 4 – Neural Network Theory
Lesson 12 – The Holy Grail
Lesson 13 – How Often to Retrain Nets
Lesson 14 – Ten Commandments of Non-linear Modeling and Neural Nets
Chapter 5 – When is the Model Ready?
Lesson 15 – The Trading Decision
Lesson 16 – Steve Ward’s Favorite Evaluation Procedure
Chapter 6 – Advanced Topics
Lesson 17 – Ensemble Nets*
Lesson 18 – Ensemble Trading Systems
Lesson 19 – Stops, Limits, and Trailing Stops
Lesson 20 – Overfitting and Curve Fitting
Lesson 21 – Continuous and Adjusted Futures Contracts
Chapter 7 – Genetic Algorithm Theory
Lesson 22 – Natural Adaptations
Lesson 23 – Sex and Reproduction
Lesson 24 – GAs Differ from Traditional Optimization Techniques
Chapter 8 – Optimizing Simple Trading Systems
Lesson 25 – In and Out-of-Sample Backtesting*
Lesson 26 – Parameter Search*
Lesson 27 – Rule Selection*
Lesson 28 – Full Optimization
Chapter 9 – Neural Network Optimization
Lesson 29 – Parameter Search
Lesson 30 – Indicator Selection*
Lesson 31 – Full Optimization
Lesson 32 – Setting Hidden Neurons*
Lesson 33 – Optimization Sets*
Chapter 10 – Advanced Optimization Techniques
Lesson 34 – Fitness Functions*
Lesson 35 – The Optimizer Isn’t Working
Lesson 36 – Fixing Over Optimization*
Chapter 11 – Programming Interface
Lesson 37 – Building and Calling External DLLs
Lesson 38 – DLL Function
Lesson 39 – Building Custom Indicators to Call DLLs
Some lessons include multiple slides. Each slide will be accompanied by an audio clip. Lessons marked with an asterisk (*) include at least one video clip.
*******************************************************
IV. Solid investments – Opinion from CEO Steve Ward
As a boy in the 1950s, my grandfather taught me about the stock market. He taught me how to put away a few dollars each month in blue chip stocks with a great future, such as AT&T. He made a lot of money on AT&T, relatively speaking. Through the years it showed steady appreciation, not to mention the regular dividends it paid. His investments paid off well in those days, which is why you always hear brokers saying things like “Over time the stock market has been the best investment blah blah blah”, or “Long term investment in quality stocks blah blah blah”.
If my grandfather were still alive I suspect he’d be rather surprised at what has been happening to AT&T stock over the past years. Ok, so maybe his trusty broker would have gotten him out of the deregulated long distance market several years ago and gotten him into more quality, like automobiles – everybody has to drive. He always drove Fords, maybe he’d have picked up some shares in that venerable company. Oh no, that’s lost half its value since the start of 1999. Surely his broker would have foreseen that and gotten him into something more stable in America. Airlines? Kmart? How about a growth industry like energy? Maybe his broker would have recommended the seventh largest company in the USA – Enron! My (ex)brokerage – the biggest name in the business – recommended a high tech fund for me in early March 2000.
I could go on but I guess you get the point. It’s not your father’s Oldsmobile and it also isn’t your father’s financial world anymore either. No wonder more and more people are doing their own trading – even futures day trading! Risky? Of course. You still think “investing” in the stock market these days isn’t risky? You have to ask “Risky compared to what?” Many of our customers already call buying stock “betting on a stock” or “placing a bet”.
I never thought I could day-trade, being stuck as I am in an office all day. Then I learned that daytrading doesn’t have to be an all day job. You can make models that get you in at a certain time, and get you out at a certain time. I make my models in evenings and on weekends using 15 minute bars. I just have to be available to read my models and make trades at pre-arranged times, right on my office computer. Once in and once out per day is fine. I’m having a ball!
Ok, you say, but you can lose a lot of money fast with futures. True, but you can make a lot fast too. You don’t have the uptick rule for shorts, and margins are much lower, significantly for day traders. On top of all that, 40% of your profit, even for intraday trades, is treated as long term capital gain!!! The best kept secret in America got better with the introduction of futures trading for the indexes (I don’t know much about pork bellies and rape seed, and the indexes are traded electronically). Futures trading may get even better with single stock futures.
*******************************************************
V. What is www.ward.net?
If you don’t already know, then you are missing out on a lot of good information. This is where you can find the latest news on new releases, tips and techniques, and the user forum. This is an important web site for all of our users, no matter which product they own. Check it out today and watch it frequently.
*******************************************************
VI. No more newsletters in the future?
No, we aren’t ending this newsletter. But you will think we did if you change your email address and don’t send us your new one!
*******************************************************