In this issue:
I. Announcing the ChaosHunter(tm)
II. Comments by Steve Ward, CEO
III. Comments by Marge Sherald, COO
IV. One way to stop this newsletter
***********************************************************
I. Announcing the ChaosHunter(tm)
In our Florida Seminar April 1-3 we announced a new product, the ChaosHunter, which can build models for science and business as well as for trading.
The ChaosHunter works by evolving formulas from basic building blocks – “atomic” functions like add, subtract, multiply, divide, sine, cosine, square root, etc. The user selects which of these functions will be in the pool of available functions, and the ChaosHunter evolves combinations that continually get better at solving the problem.
Solving the problem can mean predicting or classifying a time series for business and science users (primarily), or it can mean generating buy/sell signals for trading. Since the formulas that get generated are usually not esoteric like neural network formulas, you can show them to your boss, modify them, and insert them into other programs.
The ChaosHunter’s atomic function set contains simple polynomials, neurons, boolean functions, and many more. The neuron functions (if chosen) can combine to form unique neural net structures.
The trading models it builds can be used standalone or in conjunction with NeuroShell Trader Professional or DayTrader Professional, and they are capable of investigating chaotic time series.
You will find the complete ChaosHunter help file/manual on our new website www.chaoshunter.com. Current owners of NeuroShell Trader or the AI Trilogy can now purchase for $995, a $200 discount from the list price. Our VIP users (those who have spent more than $4000 with us on software or services) will receive another $100 discount.
***********************************************************
II. Comments by Steve Ward, CEO
The ChaosHunter (article I above) started as a science application a little over 10 years ago, but we never brought it to the market. Last year we decided to do that when we realized with a few additions to create buy/sell signals that can be fired from NeuroShell Trader Professional, it was a great product for traders as well. So now, happily, we will have a product that can be sold to both types of researchers.
For our science and business users, you get models that have readable, understandable formulas to model the data. If the data is time series, it builds recurrent formulas necessary for most definitions of chaotic functions. Although it mostly predicts, you can classify as well if there are two classes, one of which can be described by positive numbers and the other by negative numbers.
Traders can even fire the trading models the ChaosHunter makes from any number of trading products that you may have purchased before you found out how good NeuroShell is. The reason is that ChaosHunter makes formulas that can most likely be inserted into many of these systems. So you build the model (formula) based on text files exported from NeuroShell Trader or these other systems, then use the model in real time somewhere else. Of course, we have a much easier way to insert the models into NeuroShell Trader Professional or DayTrader Professional which you will find in release 5.5 (stable beta versions are available now).
ChaosHunter builds trading models I doubt you can build anywhere else, even in NeuroShell Trader. The trading models are unsupervised, meaning that you aren’t showing it answers as we would when predicting the future value of a time series. Again, there is the recurrency necessary for chaos. Finally, this program comes closest to the wish I’ve heard most often from traders through the years: give me something that decides and creates on its own the model that should be used.
***********************************************************
III. Comments by Marge Sherald, COO
It was three days of warm weather, surf, and good times at the NeuroShell Trader Advanced Seminar in Melbourne, Florida, April 1 – 3. Unfortunately for the attendees, we missed the warm weather and surf because we were too busy discussing trading models. The weird thing is that nobody seemed to mind. Steve and I did our best to prepare to explain how neural networks, genetic algorithms, and fuzzy logic work in the NeuroShell Trader. That was just the beginning because the ensuing discussions went way beyond the prepared material. That’s when it got interesting for all concerned. Special thanks to Mark Simpson (Bowfort) and website “real traders” Dr. Ted Achacoso and Shashi Mehrotra for adding insight into the process of building successful models. All of the questions from attendees kept it lively. Many of the comments we received after the seminar said that one of the biggest benefits of attending was the personal contact with other Trader users.
To all who came, our sincere thanks for your willingness to share your ideas and trading methods. Your enthusiasm is contagious.
***********************************************************
IV. One way to stop this newsletter
It is really easy. Just change your email address and don’t tell us.
***********************************************************