|
To demonstrate huge potentials
of associative self-building neural network in prediction, and
classification we developed Artificial Foreteller of Stock and Commodities.
Associative self-building neural network works over and accumulates vast
amount of information about market, its trends, and values of different
indicators to provide end user with trade forecast.
Description
 Artificial Foreteller is a new powerful system that
demonstrates extraordinary ease of use for prediction situations in
trading. Both day-traders and long-term traders can use the system.
Artificial Foreteller analyses current input values and predicts future
values and outcomes. That means Artificial Foreteller tries to predict what will happen,
and not what already happened. In other words, we would
like to get prediction if next trade period is favorable for trade or not.
As it well known human being can operate with not more than 7 criteria at
the same time. Most of traders choose not more than three or four most
important from their point of view indicators to analyze situation at the
market. As distinct from human being Artificial Foreteller is able to
operate as many different criteria and indicators as it has been trained.
Artificial
Foreteller "remembers" thousands trade situations in its neural
network and uses them for analysis of the current one. It forms prediction
based on derived from train data set regularities and analogies among
analyzed and known situations.
Artificial
Foreteller was written in VC++ and works under MS Windows98/me/NT/2000/XP.
A virtual memory storage was developed to store neural network and let the
system to create network with size more than size of PC central memory.
With help of virtual memory storage neural network became portable and can
be transferred among different PCs.
The system provides
users with:
- Full Graphical User Interface (GUI).
- Broad range of indicators.
- Possibility for day-trading and long-term trade.
- Trends.
- Buy/sell signals.
- Prognosis on whether next period would be favorable
for trade or not.
- Use of color to separate buy and sell periods and
favorable periods for trade from unfavorable once.
- Continuous training on base of recent trade
periods.
Artificial
Foreteller has the following structure:
- Preprocessor.
- Neural Network Builder.
- Interpreter.
- GUI.
Interested parties can contact us at:e-mail
|
